fix: graph entity inheritance, SyncTaskBackend error propagation, fact_type test regressions

- Fix observation entity inheritance in get_graph_data: the unit_entities query only fetched entities for visible observation IDs, not their source memory IDs, so the inheritance loop always found an empty entity_map - Remove error swallowing in SyncTaskBackend._execute_task so test failures surface instead of being silently logged - Wrap remaining consolidation submission call sites with try/except since consolidation is non-critical for those operations - Fix test_sync_backend test to expect errors to propagate - Remove fact_type=["world"] filter from test_document_upsert_behavior and test_mentioned_at_from_context_string (same PR #848 regression) - Remove flaky marker from consolidation test (now deterministic)
ci: retrigger
2026-04-02 17:17:33 +02:00 · 2026-04-02 17:17:33 +02:00 · 2026-04-02 17:17:33 +02:00
84 changed files with 3732 additions and 12239 deletions
@@ -1,7 +1,7 @@
 """Fix per-bank vector indexes to match configured extension

 Revision ID: a4b5c6d7e8f9
-Revises: c2d3e4f5g6h7, c5d6e7f8a9b0
+Revises: d6e7f8a9b0c1
 Create Date: 2026-04-01

 Migration d5e6f7a8b9c0 hardcoded HNSW when creating per-bank partial vector
@@ -21,10 +21,7 @@ from alembic import context, op
 from sqlalchemy import text

 revision: str = "a4b5c6d7e8f9"
-# Updated: the merge migration d6e7f8a9b0c1 was renamed to d6e7f8a9b0c2
-# to avoid colliding with the case_insensitive_entities_trgm_index migration
-# that shares the same revision ID.
-down_revision: str | Sequence[str] | None = "d6e7f8a9b0c2"
+down_revision: str | Sequence[str] | None = "d6e7f8a9b0c1"
 branch_labels: str | Sequence[str] | None = None
 depends_on: str | Sequence[str] | None = None

@@ -3625,7 +3625,10 @@ class MemoryEngine(MemoryEngineInterface):
                }

        if invalidated_obs > 0:
-            await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            try:
+                await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            except Exception as e:
+                logger.warning(f"Failed to submit consolidation after document deletion for bank {bank_id}: {e}")

        return result

@@ -3759,7 +3762,10 @@ class MemoryEngine(MemoryEngineInterface):
                            )

        if invalidated_obs > 0:
-            await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            try:
+                await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            except Exception as e:
+                logger.warning(f"Failed to submit consolidation after document update for bank {bank_id}: {e}")

        return True

@@ -3821,7 +3827,14 @@ class MemoryEngine(MemoryEngineInterface):
                }

        if bank_id_for_consolidation:
-            await self.submit_async_consolidation(bank_id=bank_id_for_consolidation, request_context=request_context)
+            try:
+                await self.submit_async_consolidation(
+                    bank_id=bank_id_for_consolidation, request_context=request_context
+                )
+            except Exception as e:
+                logger.warning(
+                    f"Failed to submit consolidation after memory deletion for bank {bank_id_for_consolidation}: {e}"
+                )

        return result

@@ -3830,6 +3843,7 @@ class MemoryEngine(MemoryEngineInterface):
        bank_id: str,
        fact_type: str | None = None,
        *,
+        delete_bank_profile: bool = True,
        request_context: "RequestContext",
    ) -> dict[str, int]:
        """
@@ -3916,20 +3930,21 @@ class MemoryEngine(MemoryEngineInterface):
                        # Delete entities (cascades to unit_entities, entity_cooccurrences, memory_links with entity_id)
                        await conn.execute(f"DELETE FROM {fq_table('entities')} WHERE bank_id = $1", bank_id)

-                        # Delete the bank profile and retrieve internal_id for HNSW index cleanup
-                        internal_id = await conn.fetchval(
-                            f"DELETE FROM {fq_table('banks')} WHERE bank_id = $1 RETURNING internal_id", bank_id
-                        )
-                        if internal_id:
-                            bank_internal_id = str(internal_id)
-
                        result = {
                            "memory_units_deleted": units_count,
                            "entities_deleted": entities_count,
                            "documents_deleted": documents_count,
-                            "bank_deleted": True,
                        }

+                        if delete_bank_profile:
+                            # Delete the bank profile and retrieve internal_id for HNSW index cleanup
+                            internal_id = await conn.fetchval(
+                                f"DELETE FROM {fq_table('banks')} WHERE bank_id = $1 RETURNING internal_id", bank_id
+                            )
+                            if internal_id:
+                                bank_internal_id = str(internal_id)
+                            result["bank_deleted"] = True
+
                except Exception as e:
                    raise Exception(f"Failed to delete agent data: {str(e)}")

@@ -3940,7 +3955,10 @@ class MemoryEngine(MemoryEngineInterface):
                await bank_utils.drop_bank_vector_indexes(conn, bank_internal_id)

        if invalidated_obs > 0:
-            await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            try:
+                await self.submit_async_consolidation(bank_id=bank_id, request_context=request_context)
+            except Exception as e:
+                logger.warning(f"Failed to submit consolidation after bank deletion for bank {bank_id}: {e}")

        return result

@@ -4331,7 +4349,10 @@ class MemoryEngine(MemoryEngineInterface):
            ]

            # Get entity information — only for visible units
-            if unit_ids:
+            # Fetch entities for visible units AND their source memories
+            # (so observations can inherit entities from source memories)
+            entity_lookup_ids = unit_ids + source_memory_ids
+            if entity_lookup_ids:
                unit_entities = await conn.fetch(
                    f"""
                    SELECT ue.unit_id, e.canonical_name
@@ -4340,7 +4361,7 @@ class MemoryEngine(MemoryEngineInterface):
                    WHERE ue.unit_id = ANY($1::uuid[])
                    ORDER BY ue.unit_id
                """,
-                    unit_ids,
+                    entity_lookup_ids,
                )
            else:
                unit_entities = []
@@ -6340,6 +6361,7 @@ class MemoryEngine(MemoryEngineInterface):
        *,
        tags: list[str] | None = None,
        tags_match: str = "any",
+        detail: str = "full",
        limit: int = 100,
        offset: int = 0,
        request_context: "RequestContext",
@@ -6350,6 +6372,7 @@ class MemoryEngine(MemoryEngineInterface):
            bank_id: Bank identifier
            tags: Optional tags to filter by
            tags_match: How to match tags - 'any', 'all', or 'exact'
+            detail: Detail level - 'metadata', 'content', or 'full'
            limit: Maximum number of results
            offset: Offset for pagination
            request_context: Request context for authentication
@@ -6391,13 +6414,14 @@ class MemoryEngine(MemoryEngineInterface):
                *params,
            )

-            return [self._row_to_mental_model(row) for row in rows]
+            return [self._row_to_mental_model(row, detail=detail) for row in rows]

    async def get_mental_model(
        self,
        bank_id: str,
        mental_model_id: str,
        *,
+        detail: str = "full",
        request_context: "RequestContext",
    ) -> dict[str, Any] | None:
        """Get a single pinned mental model by ID.
@@ -6405,6 +6429,7 @@ class MemoryEngine(MemoryEngineInterface):
        Args:
            bank_id: Bank identifier
            mental_model_id: Pinned mental model UUID
+            detail: Detail level - 'metadata', 'content', or 'full'
            request_context: Request context for authentication

        Returns:
@@ -6438,7 +6463,7 @@ class MemoryEngine(MemoryEngineInterface):
                mental_model_id,
            )

-            result = self._row_to_mental_model(row) if row else None
+            result = self._row_to_mental_model(row, detail=detail) if row else None

        # Post-operation hook (usage recording)
        if result and self._operation_validator:
@@ -6836,34 +6861,45 @@ class MemoryEngine(MemoryEngineInterface):

        return result == "DELETE 1"

-    def _row_to_mental_model(self, row) -> dict[str, Any]:
-        """Convert a database row to a mental model dict."""
-        reflect_response = row.get("reflect_response")
-        # Parse JSON string to dict if needed (asyncpg may return JSONB as string)
-        if isinstance(reflect_response, str):
-            try:
-                reflect_response = json.loads(reflect_response)
-            except json.JSONDecodeError:
-                reflect_response = None
+    def _row_to_mental_model(self, row, *, detail: str = "full") -> dict[str, Any]:
+        """Convert a database row to a mental model dict.
+
+        Args:
+            row: Database row
+            detail: Detail level - 'metadata', 'content', or 'full'
+        """
+        result: dict[str, Any] = {
+            "id": str(row["id"]),
+            "bank_id": row["bank_id"],
+            "name": row["name"],
+            "tags": row["tags"] or [],
+            "last_refreshed_at": row["last_refreshed_at"].isoformat() if row["last_refreshed_at"] else None,
+            "created_at": row["created_at"].isoformat() if row["created_at"] else None,
+        }
+        if detail == "metadata":
+            return result
+
        trigger = row.get("trigger")
        if isinstance(trigger, str):
            try:
                trigger = json.loads(trigger)
            except json.JSONDecodeError:
                trigger = None
-        return {
-            "id": str(row["id"]),
-            "bank_id": row["bank_id"],
-            "name": row["name"],
-            "source_query": row["source_query"],
-            "content": row["content"],
-            "tags": row["tags"] or [],
-            "max_tokens": row.get("max_tokens"),
-            "trigger": trigger,
-            "last_refreshed_at": row["last_refreshed_at"].isoformat() if row["last_refreshed_at"] else None,
-            "created_at": row["created_at"].isoformat() if row["created_at"] else None,
-            "reflect_response": reflect_response,
-        }
+        result["source_query"] = row["source_query"]
+        result["content"] = row["content"]
+        result["max_tokens"] = row.get("max_tokens")
+        result["trigger"] = trigger
+
+        if detail == "full":
+            reflect_response = row.get("reflect_response")
+            if isinstance(reflect_response, str):
+                try:
+                    reflect_response = json.loads(reflect_response)
+                except json.JSONDecodeError:
+                    reflect_response = None
+            result["reflect_response"] = reflect_response
+
+        return result

    # =========================================================================
    # Directives - Hard rules injected into prompts
@@ -82,20 +82,16 @@ class TaskBackend(ABC):

        Args:
            task_dict: Task dictionary to execute
+
+        Raises:
+            Exception: Re-raised from executor on failure.
        """
        if self._executor is None:
            task_type = task_dict.get("type", "unknown")
            logger.warning(f"No executor registered, skipping task {task_type}")
            return

-        try:
-            await self._executor(task_dict)
-        except Exception as e:
-            task_type = task_dict.get("type", "unknown")
-            logger.error(f"Error executing task {task_type}: {e}")
-            import traceback
-
-            traceback.print_exc()
+        await self._executor(task_dict)


 class SyncTaskBackend(TaskBackend):
@@ -136,6 +136,7 @@ dev = [
    "pytest-asyncio>=1.3.0",
    "pytest-timeout>=2.4.0",
    "pytest-xdist>=3.8.0",
+    "pytest-rerunfailures>=15.0",
    "python-dotenv>=1.2.1",
    "filelock>=3.20.1",  # TOCTOU race condition fix
    "ruff>=0.8.0",
@@ -161,6 +161,7 @@ def _parse_history(hist: Any) -> list[str]:


@pytest.mark.asyncio
+@pytest.mark.flaky(reruns=2, reruns_delay=5)
 async def test_horse_farm_observation_history(memory: MemoryEngine, request_context: Any) -> None:
    """Retain a sequence of horse facts and inspect how observations evolve."""
    bank_id = f"test-horses-{uuid.uuid4().hex[:8]}"
@@ -245,13 +245,12 @@ async def test_event_date_storage(memory, request_context):

        assert len(unit_ids) > 0, "Should have created at least one memory unit"

-        # Recall the fact
+        # Recall the fact (no fact_type filter — LLM may classify as world or experience)
        result = await memory.recall_async(
            bank_id=bank_id,
            query="When did Alice complete the product launch?",
            budget=Budget.LOW,
            max_tokens=500,
-            fact_type=["world"],
            request_context=request_context,
        )

@@ -547,13 +546,12 @@ async def test_mentioned_at_from_context_string(memory, request_context):

        assert len(unit_ids) > 0, "Should create memory unit"

-        # Recall and verify mentioned_at is set
+        # Recall and verify mentioned_at is set (no fact_type filter — LLM may classify as world or experience)
        result = await memory.recall_async(
            bank_id=bank_id,
            query="What does Alice like?",
            budget=Budget.LOW,
            max_tokens=500,
-            fact_type=["world"],
            request_context=request_context,
        )

@@ -738,13 +736,12 @@ async def test_context_preservation(memory, request_context):

        assert len(unit_ids) > 0, "Should create at least one memory unit"

-        # Recall and verify context is returned
+        # Recall and verify context is returned (no fact_type filter — LLM may classify as world or experience)
        result = await memory.recall_async(
            bank_id=bank_id,
            query="What did the team decide?",
            budget=Budget.LOW,
            max_tokens=500,
-            fact_type=["world"],
            request_context=request_context,
        )

@@ -1106,13 +1103,12 @@ async def test_document_upsert_behavior(memory, request_context):

        assert len(v2_units) > 0, "Should create units for v2"

-        # Recall should return the updated information
+        # Recall should return the updated information (no fact_type filter — LLM may classify as world or experience)
        result = await memory.recall_async(
            bank_id=bank_id,
            query="What is the project status?",
            budget=Budget.MID,
            max_tokens=1000,
-            fact_type=["world"],
            request_context=request_context,
        )

@@ -2060,20 +2056,23 @@ async def test_semantic_links_phase1_ann_cross_batch(memory, request_context):
    bank_id = f"test_semantic_phase1_{datetime.now(timezone.utc).timestamp()}"

    try:
-        # First batch: store some facts about Python
+        # First batch: store some world facts about a topic
+        # Use clearly "world" content (general knowledge, not personal experience)
+        # to ensure consistent fact_type classification across batches,
+        # since ANN search filters by fact_type.
        await memory.retain_async(
            bank_id=bank_id,
-            content="Alice is an expert Python developer who builds web applications using FastAPI.",
-            context="team skills",
+            content="Python is a high-level programming language widely used for web development with frameworks like FastAPI.",
+            context="programming languages",
            request_context=request_context,
        )

-        # Second batch: store similar facts — Phase 1 ANN should find the first batch's
+        # Second batch: store similar world facts — Phase 1 ANN should find the first batch's
        # facts via HNSW index and create cross-batch semantic links
        unit_ids_2 = await memory.retain_async(
            bank_id=bank_id,
-            content="Bob specializes in Python programming and creates REST APIs with FastAPI.",
-            context="team skills",
+            content="FastAPI is a modern Python web framework known for its high performance and automatic API documentation.",
+            context="programming languages",
            request_context=request_context,
        )

@@ -952,8 +952,8 @@ class TestSyncTaskBackend:
        assert executed[0] == task_dict

    @pytest.mark.asyncio
-    async def test_sync_backend_handles_errors(self):
-        """Test that SyncTaskBackend handles executor errors gracefully."""
+    async def test_sync_backend_propagates_errors(self):
+        """Test that SyncTaskBackend propagates executor errors instead of swallowing them."""

        async def failing_executor(task_dict):
            raise ValueError("Test error")
@@ -962,8 +962,9 @@ class TestSyncTaskBackend:
        backend.set_executor(failing_executor)
        await backend.initialize()

-        # Should not raise, error is logged
-        await backend.submit_task({"type": "test"})
+        # Should raise so callers can handle or surface the failure
+        with pytest.raises(ValueError, match="Test error"):
+            await backend.submit_task({"type": "test"})


 class TestDynamicTenantDiscovery:
@@ -1,5 +1,7 @@
 ---
 sidebar_position: 12
+title: "AutoGen Persistent Memory with Hindsight | Integration Guide"
+description: "Add long-term memory to AutoGen agents with Hindsight. Provides FunctionTool instances for retain, recall, and reflect that plug directly into AutoGen's AssistantAgent."
 ---

 # AutoGen
@@ -165,6 +165,18 @@ const config: Config = {
    ],
  ],

+  plugins: [
+    [
+      '@docusaurus/plugin-content-docs',
+      {
+        id: 'integrations',
+        path: './docs-integrations',
+        routeBasePath: 'sdks/integrations',
+        sidebarPath: false,
+      },
+    ],
+  ],
+
  themes: [
    '@docusaurus/theme-mermaid',
    [
@@ -41,7 +41,7 @@ curl -X POST "$HINDSIGHT_URL/v1/default/banks/my-bank/import" \
 # [docs:import-dry-run]
 curl -X POST "$HINDSIGHT_URL/v1/default/banks/my-bank/import?dry_run=true" \
  -H "Content-Type: application/json" \
-  -d @template.json
+  -d '{"version": "1", "bank": {"retain_mission": "Dry run test."}}'
 # [/docs:import-dry-run]

 # [docs:export-template]
@@ -15,7 +15,7 @@ import { fileURLToPath } from 'node:url';
 import { dirname } from 'node:path';

 const __dirname = dirname(fileURLToPath(import.meta.url));
-const integrationsDir = join(__dirname, '..', 'docs', 'sdks', 'integrations');
+const integrationsDir = join(__dirname, '..', 'docs-integrations');

 const IGNORED_FILES = ['_template.md', '_category_.json'];

@@ -55,7 +55,7 @@ for (const filename of files) {
 if (violations.length > 0) {
  console.error('[integration-seo] ❌ The following integration pages are missing required frontmatter:\n');
  for (const { filename, missing } of violations) {
-    console.error(`  docs/sdks/integrations/${filename} — missing: ${missing.join(', ')}`);
+    console.error(`  docs-integrations/${filename} — missing: ${missing.join(', ')}`);
  }
  console.error('\nAll integration pages must have both `title` and `description` in their frontmatter.');
  console.error('Example:\n');
@@ -179,110 +179,116 @@ const sidebars: SidebarsConfig = {
      collapsible: false,
      items: [
        {
-          type: 'doc',
-          id: 'sdks/integrations/local-mcp',
+          type: 'link',
+          href: '/sdks/integrations/local-mcp',
          label: 'Local MCP Server',
          customProps: { icon: '/img/icons/mcp.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/litellm',
+          type: 'link',
+          href: '/sdks/integrations/litellm',
          label: 'LiteLLM',
          customProps: { icon: '/img/icons/litellm.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/claude-code',
+          type: 'link',
+          href: '/sdks/integrations/claude-code',
          label: 'Claude Code',
          customProps: { icon: '/img/icons/claudecode.svg' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/codex',
+          type: 'link',
+          href: '/sdks/integrations/codex',
          label: 'OpenAI Codex CLI',
          customProps: { icon: '/img/icons/terminal.svg' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/openclaw',
+          type: 'link',
+          href: '/sdks/integrations/openclaw',
          label: 'OpenClaw',
          customProps: { icon: '/img/icons/openclaw.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/ai-sdk',
+          type: 'link',
+          href: '/sdks/integrations/ai-sdk',
          label: 'Vercel AI SDK',
          customProps: { icon: '/img/icons/vercel.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/chat',
+          type: 'link',
+          href: '/sdks/integrations/chat',
          label: 'Vercel Chat SDK',
          customProps: { icon: '/img/icons/vercel.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/crewai',
+          type: 'link',
+          href: '/sdks/integrations/crewai',
          label: 'CrewAI',
          customProps: { icon: '/img/icons/crewai.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/pydantic-ai',
+          type: 'link',
+          href: '/sdks/integrations/pydantic-ai',
          label: 'Pydantic AI',
          customProps: { icon: '/img/icons/pydanticai.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/agno',
+          type: 'link',
+          href: '/sdks/integrations/agno',
          label: 'Agno',
          customProps: { icon: '/img/icons/agno.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/hermes',
+          type: 'link',
+          href: '/sdks/integrations/hermes',
          label: 'Hermes Agent',
          customProps: { icon: '/img/icons/hermes.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/langgraph',
+          type: 'link',
+          href: '/sdks/integrations/langgraph',
          label: 'LangGraph / LangChain',
          customProps: { icon: '/img/icons/langgraph.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/nemoclaw',
+          type: 'link',
+          href: '/sdks/integrations/nemoclaw',
          label: 'NemoClaw',
          customProps: { icon: '/img/icons/nemoclaw.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/paperclip',
+          type: 'link',
+          href: '/sdks/integrations/paperclip',
          label: 'Paperclip',
          customProps: { icon: '/img/icons/nodejs.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/strands',
+          type: 'link',
+          href: '/sdks/integrations/strands',
          label: 'Strands Agents',
          customProps: { icon: '/img/icons/strands.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/ag2',
+          type: 'link',
+          href: '/sdks/integrations/ag2',
          label: 'AG2',
          customProps: { icon: '/img/icons/ag2.svg' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/llamaindex',
+          type: 'link',
+          href: '/sdks/integrations/autogen',
+          label: 'AutoGen',
+          customProps: { icon: '/img/icons/autogen.svg' },
+        },
+        {
+          type: 'link',
+          href: '/sdks/integrations/llamaindex',
          label: 'LlamaIndex',
          customProps: { icon: '/img/icons/llamaindex.png' },
        },
        {
-          type: 'doc',
-          id: 'sdks/integrations/skills',
+          type: 'link',
+          href: '/sdks/integrations/skills',
          label: 'Skills',
          customProps: { icon: '/img/icons/skills.png' },
        },
@@ -1,345 +0,0 @@
---
-sidebar_position: 1
---
-
-# LiteLLM
-
-Universal LLM memory integration via [LiteLLM](https://github.com/BerriAI/litellm). Add persistent memory to any LLM application with just a few lines of code.
-
-## Features
-
- **Universal LLM Support** - Works with 100+ LLM providers via LiteLLM (OpenAI, Anthropic, Groq, Azure, AWS Bedrock, Google Vertex AI, and more)
- **Simple Integration** - Just configure, enable, and use `hindsight_litellm.completion()`
- **Automatic Memory Injection** - Relevant memories are injected into prompts before LLM calls
- **Automatic Conversation Storage** - Conversations are stored to Hindsight for future recall
- **Two Memory Modes** - Choose between `reflect` (synthesized context) or `recall` (raw memory retrieval)
- **Direct Memory APIs** - Query, synthesize, and store memories manually
- **Native Client Wrappers** - Alternative wrappers for OpenAI and Anthropic SDKs
-
-## Installation
-
-```bash
-pip install hindsight-litellm
-```
-
-## Quick Start
-
-```python
-import hindsight_litellm
-
-# Configure and enable memory integration
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# Use the convenience wrapper - memory is automatically injected and stored
-response = hindsight_litellm.completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What did we discuss about AI?"}]
-)
-```
-
-## How It Works
-
-When you call `completion()`, the following happens automatically:
-
-1. **Memory Retrieval** - Hindsight is queried for relevant memories based on the conversation
-2. **Prompt Injection** - Memories are injected into the system message
-3. **LLM Call** - The enriched prompt is sent to the LLM
-4. **Conversation Storage** - The conversation is stored to Hindsight for future recall
-5. **Response Returned** - You receive the response as normal
-
-## Configuration Options
-
-```python
-hindsight_litellm.configure(
-    # Required
-    hindsight_api_url="http://localhost:8888",  # Hindsight API server URL
-    bank_id="my-agent",                          # Memory bank ID
-
-    api_key="your-api-key",        # Optional API key for authentication
-
-    # Optional - Memory behavior
-    store_conversations=True,      # Store conversations after LLM calls
-    inject_memories=True,          # Inject relevant memories into prompts
-    use_reflect=False,             # Use reflect API (synthesized) vs recall (raw memories)
-    reflect_include_facts=False,   # Include source facts with reflect responses
-    max_memories=None,             # Maximum memories to inject (None = unlimited)
-    max_memory_tokens=4096,        # Maximum tokens for memory context
-    recall_budget="mid",           # Recall budget: "low", "mid", "high"
-    fact_types=["world", "agent"], # Filter fact types to inject
-
-    # Optional - Bank Configuration
-    bank_name="My Agent",          # Human-readable display name for the memory bank
-    background="This agent...",    # Instructions guiding what Hindsight should remember
-
-    # Optional - Advanced
-    injection_mode="system_message",  # or "prepend_user"
-    excluded_models=["gpt-3.5*"],     # Exclude certain models
-    verbose=True,                     # Enable verbose logging and debug info
-)
-```
-
-### Bank Configuration
-
-The `background` and `bank_name` parameters configure the memory bank itself. When provided, `configure()` will automatically create or update the bank with these settings.
-
-```python
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="support-router",
-    bank_name="Customer Support Router",
-    background="""This agent routes customer support requests to the appropriate team.
-    Remember which types of issues should go to which teams (billing, technical, sales).
-    Track customer preferences for communication channels and past issue resolutions.""",
-)
-```
-
-### Memory Modes: Reflect vs Recall
-
- **Recall mode** (`use_reflect=False`, default): Retrieves raw memory facts and injects them as a numbered list. Best when you need precise, individual memories.
- **Reflect mode** (`use_reflect=True`): Synthesizes memories into a coherent context paragraph. Best for natural, conversational memory context.
-
-```python
-# Recall mode - raw memories
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=False,  # Default
-)
-# Injects: "1. [WORLD] User prefers Python\n2. [OPINION] User dislikes Java..."
-
-# Reflect mode - synthesized context
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=True,
-)
-# Injects: "Based on previous conversations, the user is a Python developer who..."
-```
-
-## Multi-Provider Support
-
-Works with any LiteLLM-supported provider:
-
-```python
-import hindsight_litellm
-
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# OpenAI
-hindsight_litellm.completion(model="gpt-4o", messages=[...])
-
-# Anthropic
-hindsight_litellm.completion(model="claude-3-5-sonnet-20241022", messages=[...])
-
-# Groq
-hindsight_litellm.completion(model="groq/llama-3.1-70b-versatile", messages=[...])
-
-# Azure OpenAI
-hindsight_litellm.completion(model="azure/gpt-4", messages=[...])
-
-# AWS Bedrock
-hindsight_litellm.completion(model="bedrock/anthropic.claude-3", messages=[...])
-
-# Google Vertex AI
-hindsight_litellm.completion(model="vertex_ai/gemini-pro", messages=[...])
-```
-
-## Direct Memory APIs
-
-### Recall - Query raw memories
-
-```python
-from hindsight_litellm import configure, recall
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-memories = recall("what projects am I working on?", budget="mid")
-for m in memories:
-    print(f"- [{m.fact_type}] {m.text}")
-```
-
-### Reflect - Get synthesized context
-
-```python
-from hindsight_litellm import configure, reflect
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = reflect("what do you know about the user's preferences?")
-print(result.text)
-```
-
-### Retain - Store memories
-
-```python
-from hindsight_litellm import configure, retain
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = retain(
-    content="User mentioned they're working on a machine learning project",
-    context="Discussion about current projects",
-)
-```
-
-### Async APIs
-
-```python
-from hindsight_litellm import arecall, areflect, aretain
-
-# Async versions of all memory APIs
-memories = await arecall("what do you know about me?")
-context = await areflect("summarize user preferences")
-result = await aretain(content="New information to remember")
-```
-
-## Native Client Wrappers
-
-Alternative to LiteLLM callbacks for direct SDK integration.
-
-### OpenAI Wrapper
-
-```python
-from openai import OpenAI
-from hindsight_litellm import wrap_openai
-
-client = OpenAI()
-wrapped = wrap_openai(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.chat.completions.create(
-    model="gpt-4",
-    messages=[{"role": "user", "content": "What do you know about me?"}]
-)
-```
-
-### Anthropic Wrapper
-
-```python
-from anthropic import Anthropic
-from hindsight_litellm import wrap_anthropic
-
-client = Anthropic()
-wrapped = wrap_anthropic(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.messages.create(
-    model="claude-3-5-sonnet-20241022",
-    max_tokens=1024,
-    messages=[{"role": "user", "content": "Hello!"}]
-)
-```
-
-## Debug Mode
-
-When `verbose=True`, you can inspect exactly what memories are being injected:
-
-```python
-from hindsight_litellm import configure, enable, completion, get_last_injection_debug
-
-configure(
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-    verbose=True,
-)
-enable()
-
-response = completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What's my favorite color?"}]
-)
-
-# Inspect what was injected
-debug = get_last_injection_debug()
-if debug:
-    print(f"Mode: {debug.mode}")           # "reflect" or "recall"
-    print(f"Injected: {debug.injected}")   # True/False
-    print(f"Results: {debug.results_count}")
-    print(f"Memory context:\n{debug.memory_context}")
-```
-
-## Context Manager
-
-```python
-from hindsight_litellm import hindsight_memory
-import litellm
-
-with hindsight_memory(bank_id="user-123"):
-    response = litellm.completion(model="gpt-4", messages=[...])
-# Memory integration automatically disabled after context
-```
-
-## Disabling and Cleanup
-
-```python
-from hindsight_litellm import disable, cleanup
-
-# Temporarily disable memory integration
-disable()
-
-# Clean up all resources (call when shutting down)
-cleanup()
-```
-
-## API Reference
-
-### Main Functions
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Configure global Hindsight settings |
-| `enable()` | Enable memory integration with LiteLLM |
-| `disable()` | Disable memory integration |
-| `is_enabled()` | Check if memory integration is enabled |
-| `cleanup()` | Clean up all resources |
-
-### Configuration Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_config()` | Get current configuration |
-| `is_configured()` | Check if Hindsight is configured |
-| `reset_config()` | Reset configuration to defaults |
-
-### Memory Functions
-
-| Function | Description |
-|----------|-------------|
-| `recall(query, ...)` | Synchronously query raw memories |
-| `arecall(query, ...)` | Asynchronously query raw memories |
-| `reflect(query, ...)` | Synchronously get synthesized memory context |
-| `areflect(query, ...)` | Asynchronously get synthesized memory context |
-| `retain(content, ...)` | Synchronously store a memory |
-| `aretain(content, ...)` | Asynchronously store a memory |
-
-### Debug Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_last_injection_debug()` | Get debug info from last memory injection |
-| `clear_injection_debug()` | Clear stored debug info |
-
-### Client Wrappers
-
-| Function | Description |
-|----------|-------------|
-| `wrap_openai(client, ...)` | Wrap OpenAI client with memory |
-| `wrap_anthropic(client, ...)` | Wrap Anthropic client with memory |
-
-## Requirements
-
- Python >= 3.10
- litellm >= 1.40.0
- A running Hindsight API server
@@ -1,193 +0,0 @@
---
-sidebar_position: 2
---
-
-# Local MCP Server
-
-Hindsight provides a fully local MCP server that runs entirely on your machine with an embedded PostgreSQL database. No external server or database setup required.
-
-This is ideal for:
- **Personal use with Claude Desktop** — Give Claude long-term memory across conversations
- **Development and testing** — Quick setup without infrastructure
- **Privacy-focused setups** — All data stays on your machine
-
-## Quick Install
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-mcp | bash -s -- \
-  --app claude-desktop \
-  --set HINDSIGHT_API_LLM_API_KEY=sk-...
-```
-
-This script will:
-1. Install [uv](https://docs.astral.sh/uv/) if not already installed
-2. Configure Claude Desktop to use the Hindsight MCP server
-3. Set the provided environment variables in the MCP configuration
-
-:::info Other MCP Applications
-The quick install script currently supports Claude Desktop only. For other MCP-compatible applications (Cursor, Cline, etc.), follow the [Manual Configuration](#manual-configuration) steps below.
-:::
-
-## Manual Configuration
-
-Add the following to your MCP client's configuration. For Claude Desktop:
-
- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Linux**: `~/.config/Claude/claude_desktop_config.json`
-
-For other MCP clients, refer to their documentation for the configuration file location.
-
-```json
-{
-  "mcpServers": {
-    "hindsight": {
-      "command": "uvx",
-      "args": ["--from", "hindsight-api", "hindsight-local-mcp"],
-      "env": {
-        "HINDSIGHT_API_LLM_API_KEY": "sk-..."
-      }
-    }
-  }
-}
-```
-
-### With Custom Bank ID
-
-By default, memories are stored in a bank called `mcp`. To use a different bank:
-
-```json
-{
-  "mcpServers": {
-    "hindsight": {
-      "command": "uvx",
-      "args": ["--from", "hindsight-api", "hindsight-local-mcp"],
-      "env": {
-        "HINDSIGHT_API_LLM_API_KEY": "sk-...",
-        "HINDSIGHT_API_MCP_LOCAL_BANK_ID": "my-personal-memory"
-      }
-    }
-  }
-}
-```
-
-## Environment Variables
-
-All standard [Hindsight configuration variables](/developer/configuration) are supported.
-
-### Local MCP Specific
-
-| Variable | Required | Default | Description |
-|----------|----------|---------|-------------|
-| `HINDSIGHT_API_MCP_LOCAL_BANK_ID` | No | `mcp` | Memory bank ID to use |
-| `HINDSIGHT_API_MCP_INSTRUCTIONS` | No | - | Additional instructions appended to both `retain` and `recall` tools |
-
-### Customizing Tool Behavior
-
-You can customize what gets stored by adding instructions to the tools. Re-run the install script with the additional `--set` flag:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-mcp | bash -s -- \
-  --app claude-desktop \
-  --set HINDSIGHT_API_LLM_API_KEY=sk-... \
-  --set HINDSIGHT_API_MCP_INSTRUCTIONS="Also store every action you take, code you write, and files you modify."
-```
-
-These instructions are appended to the default tool descriptions, guiding Claude on when and how to use the memory tools.
-
-## Available Tools
-
-### retain
-
-Store information to long-term memory. This is a **fire-and-forget** operation — it returns immediately while processing happens in the background.
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `content` | string | Yes | The fact or memory to store |
-| `context` | string | No | Category for the memory (default: `general`) |
-
-**Example:**
-```json
-{
-  "name": "retain",
-  "arguments": {
-    "content": "User's favorite color is blue",
-    "context": "preferences"
-  }
-}
-```
-
-**Response:**
-```json
-{
-  "status": "accepted",
-  "message": "Memory storage initiated"
-}
-```
-
-### recall
-
-Search memories to provide personalized responses.
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `query` | string | Yes | Natural language search query |
-| `max_tokens` | integer | No | Maximum tokens to return (default: 4096) |
-| `budget` | string | No | Search depth: `low`, `mid`, or `high` (default: `low`) |
-
-**Example:**
-```json
-{
-  "name": "recall",
-  "arguments": {
-    "query": "What are the user's color preferences?",
-    "max_tokens": 2048,
-    "budget": "mid"
-  }
-}
-```
-
-## How It Works
-
-The local MCP server:
-
-1. **Starts an embedded PostgreSQL** (pg0) on an automatically assigned port
-2. **Initializes the Hindsight memory engine** with local embeddings
-3. **Connects via stdio** to Claude Code using the MCP protocol
-
-Data is persisted in the pg0 data directory (`~/.pg0/hindsight-mcp/`), so your memories survive restarts.
-
-## Troubleshooting
-
-### "HINDSIGHT_API_LLM_API_KEY required"
-
-Make sure you've set the API key in your MCP configuration:
-
-```json
-{
-  "env": {
-    "HINDSIGHT_API_LLM_API_KEY": "sk-..."
-  }
-}
-```
-
-### Slow startup
-
-The first startup may take longer as it:
- Downloads the embedding model (~100MB)
- Initializes the PostgreSQL database
-
-Subsequent starts are faster.
-
-### Checking logs
-
-Set `HINDSIGHT_API_LOG_LEVEL=debug` for verbose output:
-
-```json
-{
-  "env": {
-    "HINDSIGHT_API_LOG_LEVEL": "debug"
-  }
-}
-```
-
-Logs are written to stderr and visible in Claude Code's MCP server output.
@@ -1,323 +0,0 @@
---
-sidebar_position: 3
---
-
-# Skills
-
-Hindsight provides an Agent Skill that gives AI coding assistants persistent memory across sessions. Skills are reusable prompt templates that agents can load when needed to gain specialized capabilities.
-
-## Supported Platforms
-
-| Platform | Skills Directory |
-|----------|-----------------|
-| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | `~/.claude/skills/` |
-| [OpenCode](https://github.com/opencode-ai/opencode) | `~/.opencode/skills/` |
-| [Codex CLI](https://github.com/openai/codex) | `~/.codex/skills/` |
-
-## Deployment Modes
-
-The skill supports two deployment modes:
-
-| Mode | Best For | Data Location |
-|------|----------|---------------|
-| **Local** | Individual developers | Your machine (`~/.pg0/`) |
-| **Cloud** | Teams sharing knowledge | Hindsight Cloud |
-
-## Quick Install
-
-### Option 1: Interactive Installer (Recommended)
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash
-```
-
-The installer will:
-1. Prompt you to select your AI coding assistant
-2. Select deployment mode (local or cloud)
-3. Configure the appropriate settings
-4. Install the skill to the appropriate directory
-
-### Install for a Specific Platform
-
-```bash
-# Claude Code (interactive mode selection)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude
-
-# OpenCode
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app opencode
-
-# Codex CLI
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app codex
-```
-
-### Install with Cloud Mode
-
-```bash
-# Direct cloud setup (skips interactive prompts for mode)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude --mode cloud
-```
-
-### Option 2: Using add-skill
-
-If you use [add-skill](https://add-skill.org/) to manage your agent skills:
-
-```bash
-# For local mode (individual developers)
-npx add-skill vectorize-io/hindsight --skill hindsight-local
-
-# For Hindsight Cloud (teams)
-npx add-skill vectorize-io/hindsight --skill hindsight-cloud
-
-# For self-hosted Hindsight servers
-npx add-skill vectorize-io/hindsight --skill hindsight-self-hosted
-```
-
-On first use, the AI will guide you through the remaining setup:
- **Local**: Run `uvx hindsight-embed configure` to set up your LLM provider
- **Cloud**: Provide your API key and bank ID
- **Self-hosted**: Provide your server URL, API key, and bank ID
-
-## What the Skill Provides
-
-Once installed, your AI assistant gains the ability to:
-
- **Retain** - Store user preferences, learnings, and procedure outcomes
- **Recall** - Search for relevant context before starting tasks
- **Reflect** - Synthesize memories into contextual answers
-
-The skill uses the `hindsight-embed` CLI which runs a lightweight local daemon with an embedded database.
-
-## How Skills Work
-
-Skills are **model-invoked**, meaning the AI assistant automatically decides when to use them based on the context of your conversation. You don't need to explicitly trigger the skill.
-
-The assistant will:
- **Store** when you share preferences, when tasks succeed/fail, or when learnings emerge
- **Recall** before starting non-trivial tasks to get relevant context
-
-### What Gets Stored
-
-The skill is optimized to store:
-
-| Category | Examples |
-|----------|----------|
-| **User Preferences** | Coding style, tool preferences, language choices |
-| **Procedure Outcomes** | Commands that worked, configurations that resolved issues |
-| **Learnings** | Bug solutions, workarounds, architecture decisions |
-
-## Architecture
-
-### Local Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-embed CLI
-    │
-    ▼
-Local Daemon (auto-started)
-    │
-    ▼
-Embedded PostgreSQL (~/.pg0/hindsight-embed/)
-```
-
-All data stays on your machine. The daemon auto-starts when needed and shuts down after inactivity.
-
-### Cloud Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-cli
-    │
-    ▼
-Hindsight Cloud API (https://api.hindsight.vectorize.io)
-    │
-    ▼
-Shared Memory Bank (team-accessible)
-```
-
-Data is stored in Hindsight Cloud and shared across your team. All team members with the same bank ID can access shared memories.
-
---
-
-## Local Mode Setup
-
-The skill uses configuration stored in `~/.hindsight/config.env`. Reconfigure anytime:
-
-```bash
-uvx hindsight-embed configure
-```
-
---
-
-## Cloud Mode Setup
-
-Cloud mode connects to [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup), allowing teams to share memories about a codebase. When one team member learns something, everyone benefits.
-
-### Prerequisites
-
-1. A Hindsight Cloud account ([sign up](https://ui.hindsight.vectorize.io/signup))
-2. An API key from your team admin
-3. A bank ID for your project (e.g., `team-acme-frontend`)
-
-### Installation
-
-Run the installer with cloud mode:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-You'll be prompted for:
-
-| Setting | Description | Example |
-|---------|-------------|---------|
-| **Cloud API URL** | Hindsight Cloud endpoint | `https://api.hindsight.vectorize.io` |
-| **API Key** | Your authentication key | `hs_xxx...` |
-| **Bank ID** | Shared memory bank for your team | `team-acme-frontend` |
-
-### Configuration Files
-
-Cloud mode creates two files:
-
-**`~/.hindsight/config`** — API connection settings (TOML format):
-```toml
-api_url = "https://api.hindsight.vectorize.io"
-api_key = "hs_xxx..."
-```
-
-**`~/.claude/skills/hindsight/SKILL.md`** — Skill definition with your bank ID baked in.
-
-### Team Setup
-
-To set up cloud mode for your team:
-
-1. **Team admin** creates a bank in Hindsight Cloud (e.g., `team-acme-frontend`)
-2. **Team admin** generates API keys for each team member
-3. **Each developer** runs the installer with their API key and the shared bank ID
-4. All team members now share the same memory bank
-
-### What to Store in Team Banks
-
-Cloud mode uses a **shared team bank**. Be thoughtful about what goes in:
-
-| Type | Examples | How to Store |
-|------|----------|--------------|
-| **Project conventions** | Linting rules, testing requirements, Node version | `"Project uses ESLint with Airbnb config"` |
-| **Team knowledge** | Architecture decisions, common pitfalls, domain logic | `"Auth module requires Redis 7+"` |
-| **Individual preferences** | Personal coding style, communication preferences | `"Alice prefers verbose commit messages"` |
-
-**Key distinction**: Project conventions apply to everyone. Individual preferences should include the person's name so the AI knows when to apply them.
-
-### Example Workflow
-
-```
-Day 1: Alice discovers a requirement
-─────────────────────────────────────
-Alice's AI assistant stores:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-  "Alice prefers explicit error handling over silent failures"
-
-Day 2: Bob starts working on auth
-─────────────────────────────────
-Bob's AI assistant recalls:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-
-Bob avoids the same issue Alice hit!
-(Alice's personal preference is stored but won't be applied to Bob)
-```
-
-### Testing Cloud Connection
-
-After installation, verify the connection:
-
-```bash
-# Store a test memory
-hindsight memory retain team-acme-frontend "Alice works at Google as a software engineer"
-
-# Recall it
-hindsight memory recall team-acme-frontend "Alice"
-```
-
-### Switching Between Banks
-
-If you work on multiple projects, you can have different skills installed for each AI assistant, or manually switch banks:
-
-```bash
-# Environment variable override (temporary)
-HINDSIGHT_API_URL=https://api.hindsight.vectorize.io \
-HINDSIGHT_API_KEY=hs_xxx \
-hindsight memory recall different-bank "query"
-```
-
-For permanent multi-bank setups, reinstall the skill with a different bank ID.
-
-## Troubleshooting
-
-### Skill not activating
-
-The skill activates based on its description matching your request. Try being explicit:
- "Remember that..." triggers storage
- "What do you know about..." triggers recall
-
-### Local Mode Issues
-
-**Daemon not starting:**
-```bash
-uvx hindsight-embed daemon status
-uvx hindsight-embed daemon logs
-```
-
-**Reconfigure LLM provider:**
-```bash
-uvx hindsight-embed configure
-```
-
-### Cloud Mode Issues
-
-**Authentication errors:**
-```bash
-# Verify your config
-cat ~/.hindsight/config
-
-# Test connection manually
-hindsight bank list
-```
-
-**Wrong bank ID:**
-
-Check your SKILL.md file to see which bank ID is configured:
-```bash
-cat ~/.claude/skills/hindsight/SKILL.md | grep "memory retain"
-```
-
-To change the bank ID, reinstall the skill:
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-**Network/firewall issues:**
-```bash
-# Test connectivity to cloud API
-curl -I https://api.hindsight.vectorize.io/health
-```
-
-## Requirements
-
-### Local Mode
- Python 3.10+ (for `uvx`)
- An LLM API key (OpenAI, Anthropic, Groq, etc.)
-
-### Cloud Mode
- Python 3.10+ (for `uvx`)
- Hindsight Cloud API key
- Network access to `https://api.hindsight.vectorize.io`
@@ -1,184 +0,0 @@
---
-sidebar_position: 8
-title: "AG2 (AutoGen) Persistent Memory with Hindsight | Integration Guide"
-description: "Add long-term persistent memory to your AG2 (AutoGen) agents with Hindsight. Automatic fact extraction, entity tracking, and recall tools that persist across conversations."
---
-
-# AG2
-
-Persistent long-term memory for [AG2](https://ag2.ai) agents (community AutoGen fork). Give your agents retain/recall/reflect tools that persist across conversations.
-
-[View Changelog →](/changelog/integrations/ag2)
-
-## Features
-
- **Drop-in Tools** — `register_hindsight_tools()` registers retain, recall, and reflect in one line
- **AG2-native** — Uses `Annotated` type hints compatible with AG2's `@register_for_llm` / `@register_for_execution` pattern
- **GroupChat Support** — Multiple agents can share a single memory bank
- **Selective Tools** — Include only the tools you need (`include_retain`, `include_recall`, `include_reflect`)
- **Simple Configuration** — Configure once globally or override per tool set
-
-## Installation
-
-```bash
-pip install hindsight-ag2
-```
-
-## Quick Start
-
-```python
-from autogen import AssistantAgent, UserProxyAgent, LLMConfig
-from hindsight_ag2 import register_hindsight_tools
-
-llm_config = LLMConfig(api_type="openai", model="gpt-4o-mini")
-
-with llm_config:
-    assistant = AssistantAgent(
-        name="assistant",
-        system_message="You are a helpful assistant with long-term memory.",
-    )
-    user_proxy = UserProxyAgent(
-        name="user",
-        human_input_mode="NEVER",
-    )
-
-# Register Hindsight memory tools on both agents
-register_hindsight_tools(
-    assistant, user_proxy,
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-)
-
-# The assistant can now use hindsight_retain, hindsight_recall, hindsight_reflect
-result = user_proxy.initiate_chat(
-    assistant,
-    message="Remember that I prefer Python over JavaScript.",
-)
-```
-
-That's it. The assistant can now store and retrieve memories across conversations.
-
-## How It Works
-
-The integration provides three AG2-compatible tool functions backed by Hindsight's API:
-
-| Tool | Hindsight | What happens |
-|------|-----------|--------------|
-| `hindsight_retain(content)` | `retain(bank_id, content, ...)` | Content is stored. Hindsight extracts facts, entities, and relationships from the raw text. |
-| `hindsight_recall(query)` | `recall(bank_id, query, ...)` | Hindsight runs semantic search, BM25, graph traversal, and reranking. Returns a numbered list of matching memories. |
-| `hindsight_reflect(query)` | `reflect(bank_id, query, ...)` | Hindsight synthesizes a reasoned answer from all relevant memories, using the bank's disposition traits. |
-
-Tools are plain Python functions with `Annotated` type hints. AG2 uses these hints to generate the tool schema that the LLM sees.
-
-## Configuration
-
-### Global Configuration
-
-```python
-from hindsight_ag2 import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-key",       # or set HINDSIGHT_API_KEY env var
-    budget="mid",              # low / mid / high
-    max_tokens=4096,
-    tags=["source:ag2"],       # default tags for retain
-)
-```
-
-### Per-Tool Overrides
-
-Constructor arguments override global configuration:
-
-```python
-from hindsight_ag2 import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-    budget="high",
-    max_tokens=8192,
-    tags=["team:alpha"],
-)
-```
-
-## GroupChat with Shared Memory
-
-Multiple agents can share a single memory bank in a GroupChat:
-
-```python
-from autogen import AssistantAgent, UserProxyAgent, GroupChat, GroupChatManager, LLMConfig
-from hindsight_ag2 import register_hindsight_tools
-
-llm_config = LLMConfig(api_type="openai", model="gpt-4o-mini")
-
-with llm_config:
-    researcher = AssistantAgent(name="researcher", system_message="You research topics.")
-    writer = AssistantAgent(name="writer", system_message="You write content.")
-    executor = UserProxyAgent(name="executor", human_input_mode="NEVER")
-
-# All agents share the same memory bank
-for agent in [researcher, writer]:
-    register_hindsight_tools(agent, executor, bank_id="team-memory")
-
-group_chat = GroupChat(agents=[researcher, writer, executor], messages=[])
-manager = GroupChatManager(groupchat=group_chat)
-```
-
-## Manual Registration
-
-For full control over how tools are registered:
-
-```python
-from hindsight_ag2 import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-)
-for tool_fn in tools:
-    assistant.register_for_llm(description=tool_fn.__doc__)(tool_fn)
-    user_proxy.register_for_execution()(tool_fn)
-```
-
-## API Reference
-
-### Configuration
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Set global connection and default settings |
-| `get_config()` | Get current configuration |
-| `reset_config()` | Reset configuration to None |
-
-### create_hindsight_tools
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured `Hindsight` client |
-| `hindsight_api_url` | from config | Hindsight API URL |
-| `api_key` | from config | API key |
-| `budget` | `"mid"` | Recall/reflect budget (low/mid/high) |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode (any/all/any_strict/all_strict) |
-| `retain_metadata` | `None` | Metadata dict for retain operations |
-| `retain_document_id` | `None` | Document ID for retain (groups/upserts memories) |
-| `recall_types` | `None` | Fact types to filter (world, experience, opinion, observation) |
-| `recall_include_entities` | `False` | Include entity information in recall results |
-| `reflect_context` | `None` | Additional context for reflect operations |
-| `reflect_max_tokens` | `max_tokens` | Max tokens for reflect results |
-| `reflect_response_schema` | `None` | JSON schema to constrain reflect output format |
-| `reflect_tags` | `recall_tags` | Tags to filter memories used in reflect |
-| `reflect_tags_match` | `recall_tags_match` | Tag matching for reflect |
-| `include_retain` | `True` | Include the retain tool |
-| `include_recall` | `True` | Include the recall tool |
-| `include_reflect` | `True` | Include the reflect tool |
-
-## Requirements
-
- Python >= 3.10
- ag2 >= 0.9.0
- A running Hindsight API server
@@ -1,188 +0,0 @@
---
-sidebar_position: 9
-title: "Agno Agent Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to Agno agents using Hindsight's retain, recall, and reflect tools. Plug into Agno's native Toolkit pattern for long-term memory across sessions."
---
-
-# Agno
-
-Persistent memory tools for [Agno](https://github.com/agno-agi/agno) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — using Agno's native Toolkit pattern.
-
-## Features
-
- **Native Toolkit** - Extends Agno's `Toolkit` base class, just like `Mem0Tools`
- **Memory Instructions** - Pre-recall memories for injection into `Agent(instructions=[...])`
- **Three Memory Tools** - Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Flexible Bank Resolution** - Static bank ID, `RunContext.user_id`, or custom resolver
- **Simple Configuration** - Configure once globally, or pass a client directly
-
-## Installation
-
-```bash
-pip install hindsight-agno
-```
-
-## Quick Start
-
-```python
-from agno.agent import Agent
-from agno.models.openai import OpenAIChat
-from hindsight_agno import HindsightTools
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-
-agent.print_response("Remember that I prefer dark mode")
-agent.print_response("What are my preferences?")
-```
-
-The agent now has three tools it can call:
-
- **`retain_memory`** — Store information to long-term memory
- **`recall_memory`** — Search long-term memory for relevant facts
- **`reflect_on_memory`** — Synthesize a reasoned answer from memories
-
-## With Memory Instructions
-
-Pre-recall relevant memories and inject them into the system prompt:
-
-```python
-from hindsight_agno import HindsightTools, memory_instructions
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-    instructions=[memory_instructions(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = [HindsightTools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-    enable_retain=True,
-    enable_recall=True,
-    enable_reflect=False,  # Omit reflect
-)]
-```
-
-## Bank Resolution
-
-The bank ID is resolved in order:
-
-1. **`bank_resolver`** — Custom callable `(RunContext) -> str`
-2. **`bank_id`** — Static bank ID passed to constructor
-3. **`run_context.user_id`** — Automatic per-user banks
-
-```python
-# Per-user banks from RunContext
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(hindsight_api_url="http://localhost:8888")],
-    user_id="user-123",  # Used as bank_id
-)
-
-# Custom resolver
-def resolve_bank(ctx):
-    return f"team-{ctx.user_id}"
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_resolver=resolve_bank,
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-```
-
-## Global Configuration
-
-Instead of passing connection details to every toolkit, configure once:
-
-```python
-from hindsight_agno import configure, HindsightTools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create toolkit without passing connection details
-tools = [HindsightTools(bank_id="user-123")]
-```
-
-## Configuration Reference
-
-### `HindsightTools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static Hindsight memory bank ID |
-| `bank_resolver` | `None` | Callable `(RunContext) -> str` for dynamic bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `enable_retain` | `True` | Include the retain (store) tool |
-| `enable_recall` | `True` | Include the recall (search) tool |
-| `enable_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- agno
- hindsight-client >= 0.4.0
- A running Hindsight API server
@@ -1,101 +0,0 @@
---
-sidebar_position: 4
-title: "Vercel AI SDK Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to any Vercel AI SDK application with five ready-to-use Hindsight tools. Retain conversations, recall context, and reflect on past interactions — works with any model."
---
-
-# Vercel AI SDK
-
-The `@vectorize-io/hindsight-ai-sdk` package integrates [Hindsight](https://hindsight.vectorize.io) memory with the [Vercel AI SDK](https://ai-sdk.dev). It provides five ready-to-use tools for retaining, recalling, and reflecting on long-term memories.
-
-[View Changelog →](/changelog/integrations/ai-sdk)
-
-import CodeSnippet from '@site/src/components/CodeSnippet';
-
-import aiSdkTs from '!!raw-loader!@site/examples/integrations/ai-sdk.ts';
-
-## Installation
-
-```bash
-npm install @vectorize-io/hindsight-ai-sdk @vectorize-io/hindsight-client ai
-```
-
-## Setup
-
-Create a Hindsight client and pass it to `createHindsightTools` along with a `bankId`. The `bankId` identifies the memory store for this session—typically a user ID.
-
-<CodeSnippet code={aiSdkTs} section="setup" language="typescript" />
-
-:::tip Per-request bank IDs
-In multi-user applications, create `tools` inside your request handler so each request closes over the correct `bankId`. See the [Next.js example](#in-a-nextjs-route-handler) below.
-:::
-
-## Usage
-
-### With `generateText`
-
-<CodeSnippet code={aiSdkTs} section="generate-text" language="typescript" />
-
-### With `streamText`
-
-<CodeSnippet code={aiSdkTs} section="stream-text" language="typescript" />
-
-### With `ToolLoopAgent`
-
-<CodeSnippet code={aiSdkTs} section="tool-loop-agent" language="typescript" />
-
-### In a Next.js Route Handler
-
-<CodeSnippet code={aiSdkTs} section="next-api-route" language="typescript" />
-
---
-
-## Tools Reference
-
-Five tools are registered. The `bankId` is fixed at creation time—the agent cannot change it.
-
-| Tool | What the agent provides | What the constructor controls |
-|------|------------------------|-------------------------------|
-| `retain` | `content`, `documentId`, `timestamp`, `context` | `async`, `tags`, `metadata` |
-| `recall` | `query`, `queryTimestamp` | `budget`, `types`, `maxTokens`, `includeEntities`, `includeChunks` |
-| `reflect` | `query`, `context` | `budget` |
-| `getMentalModel` | `mentalModelId` | — |
-| `getDocument` | `documentId` | — |
-
-**Why this split?** Semantic inputs (what to remember, what to search for) belong to the agent. Infrastructure concerns (cost budget, tagging strategy, async mode) belong to the application.
-
---
-
-## Constructor Options
-
-All options except `client` and `bankId` are optional. Each tool's options are grouped under the tool name.
-
-<CodeSnippet code={aiSdkTs} section="constructor-options" language="typescript" />
-
-### `retain`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `async` | `boolean` | `false` | Fire-and-forget — do not wait for ingestion to complete |
-| `tags` | `string[]` | — | Tags attached to every retained memory |
-| `metadata` | `Record<string, string>` | — | Metadata attached to every retained memory |
-| `description` | `string` | built-in | Override the tool description shown to the model |
-
-### `recall`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Controls retrieval depth and latency |
-| `types` | `('world' \| 'experience' \| 'observation')[]` | all | Restrict results to these fact types |
-| `maxTokens` | `number` | API default | Cap the total tokens returned |
-| `includeEntities` | `boolean` | `false` | Include entity observations in results |
-| `includeChunks` | `boolean` | `false` | Include raw source chunks in results |
-| `description` | `string` | built-in | Override the tool description shown to the model |
-
-### `reflect`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Controls synthesis depth and latency |
-| `maxTokens` | `number` | API default | Maximum tokens for the response |
-| `description` | `string` | built-in | Override the tool description shown to the model |
@@ -1,167 +0,0 @@
---
-sidebar_position: 5
-title: "Vercel Chat SDK Persistent Memory with Hindsight | Integration"
-description: "Give your Vercel Chat SDK bot persistent, per-user memory across Slack, Discord, Teams, and more. Single handler wrapper, no custom plumbing required."
---
-
-# Vercel Chat SDK
-
-We built `@vectorize-io/hindsight-chat` to give [Vercel Chat SDK](https://github.com/vercel/chat) bots persistent, per-user memory with a single handler wrapper. The integration works across Slack, Discord, Teams, Google Chat, GitHub, and Linear — no custom plumbing required.
-
-[View Changelog →](/changelog/integrations/chat)
-
-## Installation
-
-```bash
-npm install @vectorize-io/hindsight-chat
-```
-
-## Quick Start
-
-```typescript
-import { Chat } from 'chat';
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-import { withHindsightChat } from '@vectorize-io/hindsight-chat';
-import { streamText } from 'ai';
-import { openai } from '@ai-sdk/openai';
-
-const chat = new Chat({ connectors: [/* your connectors */] });
-const hindsight = new HindsightClient({ apiKey: process.env.HINDSIGHT_API_KEY });
-
-chat.onNewMention(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId, // per-user memory
-    },
-    async (thread, message, ctx) => {
-      await thread.subscribe();
-
-      const result = await streamText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-
-      // Stream the response
-      const chunks: string[] = [];
-      for await (const chunk of result.textStream) {
-        chunks.push(chunk);
-      }
-      const fullResponse = chunks.join('');
-      await thread.post(fullResponse);
-
-      // Store the conversation in memory
-      await ctx.retain(
-        `User: ${message.text}\nAssistant: ${fullResponse}`
-      );
-    }
-  )
-);
-```
-
-## Configuration
-
-### `withHindsightChat(options, handler)`
-
-`withHindsightChat` wraps your existing Chat SDK handler and injects memory context automatically. It returns a standard handler `(thread, message) => Promise<void>` so it drops in without changing your handler signature.
-
-#### Options
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `client` | `HindsightClient` | *required* | Hindsight client instance |
-| `bankId` | `string \| (msg) => string` | *required* | Memory bank ID or resolver function |
-| `recall.enabled` | `boolean` | `true` | Auto-recall memories before handler |
-| `recall.budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Processing budget for recall |
-| `recall.maxTokens` | `number` | API default | Max tokens for recall results |
-| `recall.types` | `FactType[]` | all | Filter to specific fact types |
-| `recall.includeEntities` | `boolean` | `true` | Include entity observations |
-| `retain.enabled` | `boolean` | `false` | Auto-retain inbound messages |
-| `retain.async` | `boolean` | `true` | Fire-and-forget retain |
-| `retain.tags` | `string[]` | – | Tags for retained memories |
-| `retain.metadata` | `Record<string, string>` | – | Metadata for retained memories |
-
-### Context (`ctx`)
-
-We inject a third `ctx` argument into your handler that exposes the full Hindsight memory API scoped to the current user's bank:
-
-| Property/Method | Description |
-|----------------|-------------|
-| `ctx.bankId` | Resolved bank ID |
-| `ctx.memories` | Array of recalled memories |
-| `ctx.entities` | Entity observations (or null) |
-| `ctx.memoriesAsSystemPrompt(options?)` | Format memories for LLM system prompt |
-| `ctx.retain(content, options?)` | Store content in memory |
-| `ctx.recall(query, options?)` | Search memories |
-| `ctx.reflect(query, options?)` | Reason over memories |
-
-## Examples
-
-### Subscribed Message Handler
-
-```typescript
-chat.onSubscribedMessage(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId,
-      recall: { budget: 'high', maxTokens: 1000 },
-    },
-    async (thread, message, ctx) => {
-      const result = await generateText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-      await thread.post(result.text);
-    }
-  )
-);
-```
-
-### Auto-Retain Inbound Messages
-
-```typescript
-chat.onNewMention(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId,
-      retain: { enabled: true, tags: ['slack', 'inbound'] },
-    },
-    async (thread, message, ctx) => {
-      // Inbound message is already being retained automatically
-      const result = await generateText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-      await thread.post(result.text);
-
-      // Retain the assistant response separately
-      await ctx.retain(`Assistant: ${result.text}`, {
-        tags: ['slack', 'outbound'],
-      });
-    }
-  )
-);
-```
-
-### Static Bank ID (Shared Memory)
-
-```typescript
-// All users share the same memory bank
-chat.onNewMention(
-  withHindsightChat(
-    { client: hindsight, bankId: 'shared-team-memory' },
-    async (thread, message, ctx) => {
-      // ...
-    }
-  )
-);
-```
-
-## Error Handling
-
-We designed the integration so that memory failures never break your bot. Auto-recall and auto-retain errors are caught internally, logged as warnings, and the handler continues with empty memories. Manual `ctx.retain()`, `ctx.recall()`, and `ctx.reflect()` calls propagate errors normally so you can handle them as needed.
@@ -1,216 +0,0 @@
---
-sidebar_position: 5
-title: "Claude Code Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Claude Code with Hindsight. Automatically captures conversations and recalls relevant context across sessions using Claude Code's hook-based architecture."
---
-
-# Claude Code
-
-Biomimetic long-term memory for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) using [Hindsight](https://vectorize.io/hindsight). Automatically captures conversations and intelligently recalls relevant context — a complete port of [`hindsight-openclaw`](./openclaw) adapted to Claude Code's hook-based plugin architecture.
-
-[View Changelog →](/changelog/integrations/claude-code)
-
-## Quick Start
-
-```bash
-# 1. Add the Hindsight marketplace and install the plugin
-claude plugin marketplace add vectorize-io/hindsight
-claude plugin install hindsight-memory
-
-# 2. Configure your LLM provider for memory extraction
-# Option A: OpenAI (auto-detected)
-export OPENAI_API_KEY="sk-your-key"
-
-# Option B: Anthropic (auto-detected)
-export ANTHROPIC_API_KEY="your-key"
-
-# Option C: No API key needed (uses Claude Code's own model — personal/local use only)
-export HINDSIGHT_LLM_PROVIDER=claude-code
-
-# Option D: Connect to an external Hindsight server instead of running locally
-mkdir -p ~/.hindsight
-echo '{"hindsightApiUrl": "https://your-hindsight-server.com"}' > ~/.hindsight/claude-code.json
-
-# 3. Start Claude Code — the plugin activates automatically
-claude
-```
-
-That's it! The plugin will automatically start capturing and recalling memories.
-
-## Features
-
- **Auto-recall** — on every user prompt, queries Hindsight for relevant memories and injects them as context (invisible to the chat transcript, visible to Claude)
- **Auto-retain** — after every response (or every N turns), extracts and retains conversation content to Hindsight for long-term storage
- **Daemon management** — can auto-start/stop `hindsight-embed` locally or connect to an external Hindsight server
- **Dynamic bank IDs** — supports per-agent, per-project, or per-session memory isolation
- **Channel-agnostic** — works with Claude Code Channels (Telegram, Discord, Slack) or interactive sessions
- **Zero dependencies** — pure Python stdlib, no pip install required
-
-## Architecture
-
-The plugin uses all four Claude Code hook events:
-
-| Hook | Event | Purpose |
-|------|-------|---------|
-| `session_start.py` | `SessionStart` | Health check — verify Hindsight is reachable |
-| `recall.py` | `UserPromptSubmit` | **Auto-recall** — query memories, inject as `additionalContext` |
-| `retain.py` | `Stop` | **Auto-retain** — extract transcript, POST to Hindsight (async) |
-| `session_end.py` | `SessionEnd` | Cleanup — stop auto-managed daemon if started |
-
-## Connection Modes
-
-### 1. External API (recommended for production)
-
-Connect to a running Hindsight server (cloud or self-hosted). No local LLM needed — the server handles fact extraction.
-
-```json
-{
-  "hindsightApiUrl": "https://your-hindsight-server.com",
-  "hindsightApiToken": "your-token"
-}
-```
-
-### 2. Local Daemon (auto-managed)
-
-The plugin automatically starts and stops `hindsight-embed` via `uvx`. Requires an LLM provider API key for local fact extraction.
-
-Set an LLM provider:
-```bash
-export OPENAI_API_KEY="sk-your-key"
-# or
-export ANTHROPIC_API_KEY="your-key"
-# or
-export HINDSIGHT_LLM_PROVIDER=claude-code # No API key needed
-```
-
-The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_LLM_MODEL`.
-
-### 3. Existing Local Server
-
-If you already have `hindsight-embed` running, leave `hindsightApiUrl` empty and set `apiPort` to match your server's port. The plugin will detect it automatically.
-
-## Configuration
-
-All settings live in `~/.hindsight/claude-code.json`. Every setting can also be overridden via environment variables. The plugin ships with sensible defaults — you only need to configure what you want to change.
-
-**Loading order** (later entries win):
-1. Built-in defaults (hardcoded in the plugin)
-2. Plugin `settings.json` (ships with the plugin, at `CLAUDE_PLUGIN_ROOT/settings.json`)
-3. User config (`~/.hindsight/claude-code.json` — recommended for your overrides)
-4. Environment variables
-
---
-
-### Connection & Daemon
-
-These settings control how the plugin connects to the Hindsight API.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | `HINDSIGHT_API_URL` | `""` (empty) | URL of an external Hindsight API server. When empty, the plugin uses a local daemon instead. |
-| `hindsightApiToken` | `HINDSIGHT_API_TOKEN` | `null` | Authentication token for the external API. Only needed when `hindsightApiUrl` is set. |
-| `apiPort` | `HINDSIGHT_API_PORT` | `9077` | Port used by the local `hindsight-embed` daemon. Change this if you run multiple instances or have a port conflict. |
-| `daemonIdleTimeout` | `HINDSIGHT_DAEMON_IDLE_TIMEOUT` | `0` | Seconds of inactivity before the local daemon shuts itself down. `0` means the daemon stays running until the session ends. |
-| `embedVersion` | `HINDSIGHT_EMBED_VERSION` | `"latest"` | Which version of `hindsight-embed` to install via `uvx`. Pin to a specific version (e.g. `"0.5.2"`) for reproducibility. |
-| `embedPackagePath` | `HINDSIGHT_EMBED_PACKAGE_PATH` | `null` | Local filesystem path to a `hindsight-embed` checkout. When set, the plugin runs from this path instead of installing via `uvx`. Useful for development. |
-
---
-
-### LLM Provider (local daemon only)
-
-These settings configure which LLM the local daemon uses for fact extraction. They are **ignored** when connecting to an external API (the server uses its own LLM configuration).
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `llmProvider` | `HINDSIGHT_LLM_PROVIDER` | auto-detect | Which LLM provider to use. Supported values: `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `openai-codex`, `claude-code`. When omitted, the plugin auto-detects by checking for API key env vars in order: `OPENAI_API_KEY` → `ANTHROPIC_API_KEY` → `GEMINI_API_KEY` → `GROQ_API_KEY`. |
-| `llmModel` | `HINDSIGHT_LLM_MODEL` | provider default | Override the default model for the chosen provider (e.g. `"gpt-4o"`, `"claude-sonnet-4-20250514"`). When omitted, the Hindsight API picks a sensible default for each provider. |
-| `llmApiKeyEnv` | — | provider standard | Name of the environment variable that holds the API key. Normally auto-detected (e.g. `OPENAI_API_KEY` for the `openai` provider). Set this only if your key is in a non-standard env var. |
-
---
-
-### Memory Bank
-
-A **bank** is an isolated memory store — like a separate "brain." These settings control which bank the plugin reads from and writes to.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `bankId` | `HINDSIGHT_BANK_ID` | `"claude_code"` | The bank ID to use when `dynamicBankId` is `false`. All sessions share this single bank. |
-| `bankMission` | `HINDSIGHT_BANK_MISSION` | generic assistant prompt | A short description of the agent's identity and purpose. Sent to Hindsight when creating or updating the bank, and used during recall to contextualize results. |
-| `retainMission` | — | extraction prompt | Instructions for the fact extraction LLM — tells it *what* to extract from conversations (e.g. "Extract technical decisions and user preferences"). |
-| `dynamicBankId` | `HINDSIGHT_DYNAMIC_BANK_ID` | `false` | When `true`, the plugin derives a unique bank ID from context fields (see `dynamicBankGranularity`), giving each combination its own isolated memory. |
-| `dynamicBankGranularity` | — | `["agent", "project"]` | Which context fields to combine when building a dynamic bank ID. Available fields: `agent` (agent name), `project` (working directory), `session` (session ID), `channel` (channel ID), `user` (user ID). |
-| `bankIdPrefix` | — | `""` | A string prepended to all bank IDs — both static and dynamic. Useful for namespacing (e.g. `"prod"` or `"staging"`). |
-| `agentName` | `HINDSIGHT_AGENT_NAME` | `"claude-code"` | Name used for the `agent` field in dynamic bank ID derivation. |
-
---
-
-### Auto-Recall
-
-Auto-recall runs on every user prompt. It queries Hindsight for relevant memories and injects them into Claude's context as invisible `additionalContext` (the user doesn't see them in the chat transcript).
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `HINDSIGHT_AUTO_RECALL` | `true` | Master switch for auto-recall. Set to `false` to disable memory retrieval entirely. |
-| `recallBudget` | `HINDSIGHT_RECALL_BUDGET` | `"mid"` | Controls how hard Hindsight searches for memories. `"low"` = fast, fewer strategies; `"mid"` = balanced; `"high"` = thorough, slower. Affects latency directly. |
-| `recallMaxTokens` | `HINDSIGHT_RECALL_MAX_TOKENS` | `1024` | Maximum number of tokens in the recalled memory block. Lower values reduce context usage but may truncate relevant memories. |
-| `recallTypes` | — | `["world", "experience"]` | Which memory types to retrieve. `"world"` = general facts; `"experience"` = personal experiences; `"observation"` = raw observations. |
-| `recallContextTurns` | `HINDSIGHT_RECALL_CONTEXT_TURNS` | `1` | How many prior conversation turns to include when composing the recall query. `1` = only the latest user message; higher values give more context but may dilute the query. |
-| `recallMaxQueryChars` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | `800` | Maximum character length of the query sent to Hindsight. Longer queries are truncated. |
-| `recallRoles` | — | `["user", "assistant"]` | Which message roles to include when building the recall query from prior turns. |
-| `recallPromptPreamble` | — | built-in string | Text placed above the recalled memories in the injected context block. Customize this to change how Claude interprets the memories. |
-
---
-
-### Auto-Retain
-
-Auto-retain runs after Claude responds. It extracts the conversation transcript and sends it to Hindsight for long-term storage and fact extraction.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `HINDSIGHT_AUTO_RETAIN` | `true` | Master switch for auto-retain. Set to `false` to disable memory storage entirely. |
-| `retainMode` | `HINDSIGHT_RETAIN_MODE` | `"full-session"` | Retention strategy. `"full-session"` sends the full conversation transcript (with chunking). |
-| `retainEveryNTurns` | — | `10` | How often to retain. `1` = every turn; `10` = every 10th turn. Higher values reduce API calls but delay memory capture. Values > 1 enable **chunked retention** with a sliding window. |
-| `retainOverlapTurns` | — | `2` | When chunked retention fires, this many extra turns from the previous chunk are included for continuity. Total window size = `retainEveryNTurns + retainOverlapTurns`. |
-| `retainRoles` | — | `["user", "assistant"]` | Which message roles to include in the retained transcript. |
-| `retainToolCalls` | — | `true` | Whether to include tool calls (function invocations and results) in the retained transcript. Captures structured actions like file reads, searches, and code edits. |
-| `retainTags` | — | `["{session_id}"]` | Tags attached to the retained document. Supports `{session_id}` placeholder which is replaced with the current session ID at runtime. |
-| `retainMetadata` | — | `{}` | Arbitrary key-value metadata attached to the retained document. |
-| `retainContext` | — | `"claude-code"` | A label attached to retained memories identifying their source. Useful when multiple integrations write to the same bank. |
-
---
-
-### Debug
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `debug` | `HINDSIGHT_DEBUG` | `false` | Enable verbose logging to stderr. All log lines are prefixed with `[Hindsight]`. Useful for diagnosing connection issues, recall/retain behavior, and bank ID derivation. |
-
-## Claude Code Channels
-
-With [Claude Code Channels](https://docs.anthropic.com/en/docs/claude-code), Claude Code can operate as a persistent background agent connected to Telegram, Discord, Slack, and other messaging platforms. This plugin gives Channel-based agents the same long-term memory that `hindsight-openclaw` provides for Openclaw agents.
-
-For Channel agents, enable dynamic bank IDs for per-channel/per-user memory isolation:
-
-```json
-{
-  "dynamicBankId": true,
-  "dynamicBankGranularity": ["agent", "channel", "user"]
-}
-```
-
-And set channel context via environment variables:
-
-```bash
-export HINDSIGHT_CHANNEL_ID="telegram-group-12345"
-export HINDSIGHT_USER_ID="user-67890"
-```
-
-## Troubleshooting
-
-**Plugin not activating**: Check Claude Code logs for `[Hindsight]` messages. Enable `"debug": true` in `~/.hindsight/claude-code.json`.
-
-**Recall returning no memories**: Verify the Hindsight server is reachable (`curl http://localhost:9077/health`). Memories need at least one retain cycle before they're available.
-
-**Daemon not starting**: Ensure an LLM API key is set (or use `HINDSIGHT_LLM_PROVIDER=claude-code`). Review daemon logs at `~/.hindsight/profiles/claude-code.log`.
-
-**High latency on recall**: The recall hook has a 12-second timeout. Use `recallBudget: "low"` or reduce `recallMaxTokens` for faster responses.
@@ -1,184 +0,0 @@
---
-sidebar_position: 6
-title: "Codex CLI Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to OpenAI Codex CLI with Hindsight. Three Python hook scripts automatically recall context before each prompt and retain conversations — no workflow changes required."
---
-
-# Codex
-
-[View Changelog →](/changelog/integrations/codex)
-
-Persistent memory for [Codex CLI](https://github.com/openai/codex) using [Hindsight](https://vectorize.io/hindsight). Three Python hook scripts automatically recall relevant context before each prompt and retain conversations after each turn — no changes to your Codex workflow required.
-
-## Quick Start
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-codex | bash
-```
-
-The installer will guide you through choosing local or cloud mode and configuring your connection. Once installed, start a new Codex session — memory is live.
-
-To uninstall:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-codex | bash -s -- --uninstall
-```
-
-## Features
-
- **Auto-recall** — on every user prompt, queries Hindsight for relevant memories and injects them as `additionalContext` (invisible to the transcript, visible to Codex)
- **Auto-retain** — after each Codex response, stores the conversation transcript to Hindsight for future recall
- **Dynamic bank IDs** — supports per-project memory isolation based on the working directory
- **Session-level upsert** — uses the session ID as the document ID so re-running the same session updates rather than duplicates stored content
- **Zero dependencies** — pure Python stdlib, no pip install required
-
-## Architecture
-
-The plugin uses three Codex hook events:
-
-| Hook | Event | Purpose |
-|------|-------|---------|
-| `session_start.py` | `SessionStart` | Warm up — verify Hindsight is reachable |
-| `recall.py` | `UserPromptSubmit` | **Auto-recall** — query memories, inject as `additionalContext` |
-| `retain.py` | `Stop` | **Auto-retain** — extract transcript, POST to Hindsight (async) |
-
-On `UserPromptSubmit`, the hook reads the prompt, queries Hindsight for the most relevant memories, and outputs a `hookSpecificOutput.additionalContext` block. Codex prepends this to the conversation before sending it to the model:
-
-```
-<hindsight_memories>
-Relevant memories from past conversations...
-Current time - 2026-03-27 09:14
-
- Project uses FastAPI with asyncpg — not SQLAlchemy [world] (2026-03-26)
- Preferred testing framework: pytest with pytest-asyncio [experience] (2026-03-26)
-</hindsight_memories>
-```
-
-On `Stop`, the hook reads the session transcript, strips previously injected memory tags (to prevent feedback loops), and POSTs the conversation to Hindsight asynchronously.
-
-## Connection Modes
-
-### 1. External API (recommended)
-
-Connect to a running Hindsight server (cloud or self-hosted):
-
-```json
-{
-  "hindsightApiUrl": "https://api.hindsight.vectorize.io",
-  "hindsightApiToken": "hsk_your_token"
-}
-```
-
-### 2. Local Daemon
-
-Run `hindsight-embed` locally. The `session_start.py` hook will detect it on `apiPort` (default `9077`). The daemon is not auto-started by the Codex plugin — start it separately:
-
-```bash
-uvx hindsight-embed
-```
-
-Then leave `hindsightApiUrl` empty in your config and the plugin will connect to `http://localhost:9077`.
-
-## Configuration
-
-Settings are loaded from `~/.hindsight/codex.json`. Every setting can also be overridden via environment variable.
-
-**Loading order** (later entries win):
-
-1. Built-in defaults
-2. Plugin `settings.json` (at `~/.hindsight/codex/settings.json`)
-3. User config (`~/.hindsight/codex.json`)
-4. Environment variables
-
---
-
-### Connection
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | `HINDSIGHT_API_URL` | `""` | URL of the Hindsight API server. Required. |
-| `hindsightApiToken` | `HINDSIGHT_API_TOKEN` | `null` | API token for authentication. Required for Hindsight Cloud. |
-| `apiPort` | `HINDSIGHT_API_PORT` | `9077` | Port for the local `hindsight-embed` daemon. |
-
---
-
-### Memory Bank
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `bankId` | `HINDSIGHT_BANK_ID` | `"codex"` | The bank to read from and write to. All sessions share this bank unless `dynamicBankId` is enabled. |
-| `bankMission` | `HINDSIGHT_BANK_MISSION` | coding assistant prompt | Describes the agent's purpose. Sent when creating or updating the bank. |
-| `retainMission` | — | extraction prompt | Instructions for Hindsight's fact extraction — what to extract from coding conversations. |
-| `dynamicBankId` | `HINDSIGHT_DYNAMIC_BANK_ID` | `false` | When `true`, derives a unique bank ID from `dynamicBankGranularity` fields — useful for per-project isolation. |
-| `dynamicBankGranularity` | — | `["agent", "project"]` | Which fields to combine for dynamic bank IDs. `"project"` = working directory, `"agent"` = agent name. |
-| `bankIdPrefix` | — | `""` | Prefix prepended to all bank IDs. |
-| `agentName` | `HINDSIGHT_AGENT_NAME` | `"codex"` | Agent name used in dynamic bank ID derivation. |
-
---
-
-### Auto-Recall
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `HINDSIGHT_AUTO_RECALL` | `true` | Master switch for auto-recall. |
-| `recallBudget` | `HINDSIGHT_RECALL_BUDGET` | `"mid"` | Search depth: `"low"` (fast), `"mid"` (balanced), `"high"` (thorough). |
-| `recallMaxTokens` | `HINDSIGHT_RECALL_MAX_TOKENS` | `1024` | Max tokens in the recalled memory block. |
-| `recallTypes` | — | `["world", "experience"]` | Memory types to retrieve. |
-| `recallContextTurns` | `HINDSIGHT_RECALL_CONTEXT_TURNS` | `1` | Prior turns to include when building the recall query. `1` = latest prompt only. |
-| `recallMaxQueryChars` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | `800` | Max characters in the query sent to Hindsight. |
-| `recallRoles` | — | `["user", "assistant"]` | Which roles to include when building a multi-turn query. |
-| `recallPromptPreamble` | — | built-in | Text placed above the recalled memories in the injected context block. |
-
---
-
-### Auto-Retain
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `HINDSIGHT_AUTO_RETAIN` | `true` | Master switch for auto-retain. |
-| `retainMode` | `HINDSIGHT_RETAIN_MODE` | `"full-session"` | `"full-session"` sends the full transcript per session (upserted by session ID). `"chunked"` sends sliding windows every N turns. |
-| `retainEveryNTurns` | — | `10` | Retain fires every N turns. `1` = every turn. Higher values reduce API calls. |
-| `retainOverlapTurns` | — | `2` | Extra turns included from the previous chunk (chunked mode only). |
-| `retainRoles` | — | `["user", "assistant"]` | Which roles to include in the retained transcript. |
-| `retainTags` | — | `["{session_id}"]` | Tags attached to the stored document. `{session_id}` is replaced at runtime. |
-| `retainMetadata` | — | `{}` | Arbitrary key-value metadata attached to the stored document. |
-| `retainContext` | — | `"codex"` | Label identifying the source integration. Useful when multiple integrations write to the same bank. |
-
---
-
-### Debug
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `debug` | `HINDSIGHT_DEBUG` | `false` | Enable verbose logging to stderr. All log lines are prefixed with `[Hindsight]`. |
-
-## Per-Project Memory
-
-To give each project its own isolated memory bank, enable dynamic bank IDs:
-
-```json
-{
-  "dynamicBankId": true,
-  "dynamicBankGranularity": ["agent", "project"]
-}
-```
-
-With this config, running Codex in `~/projects/api` and `~/projects/frontend` stores and recalls memories separately. Bank IDs are derived from the working directory path.
-
-## Troubleshooting
-
-**Hooks not firing**: Check that `~/.codex/config.toml` contains `codex_hooks = true` under `[features]`. Re-run the installer to fix this automatically.
-
-**No memories recalled**: Recall returns results only after something has been retained. Either complete one Codex session first, or seed your bank manually using the [cookbook example](https://github.com/vectorize-io/hindsight-cookbook/tree/main/applications/codex-memory).
-
-**Memory not being stored**: `retainEveryNTurns` defaults to `10` — retain only fires every 10 turns. While testing, add `"retainEveryNTurns": 1` to `~/.hindsight/codex.json`.
-
-**Debug mode**: Add `"debug": true` to `~/.hindsight/codex.json` to see what Hindsight is doing on each turn:
-
-```
-[Hindsight] Recalling from bank 'codex', query length: 42
-[Hindsight] Injecting 3 memories
-[Hindsight] Retaining to bank 'codex', doc 'sess-abc123', 2 messages, 847 chars
-```
-
-**High latency on recall**: Use `"recallBudget": "low"` or reduce `recallMaxTokens` to speed up recall queries.
@@ -1,245 +0,0 @@
---
-sidebar_position: 5
-title: "CrewAI Persistent Memory with Hindsight | Integration Guide"
-description: "Add long-term memory to your CrewAI agent crews. Hindsight provides fact extraction, entity tracking, and temporal awareness — persisted automatically across all crew runs."
---
-
-# CrewAI
-
-Persistent memory for AI agent crews via [CrewAI](https://github.com/crewAIInc/crewAI). Give your crews long-term memory with fact extraction, entity tracking, and temporal awareness.
-
-[View Changelog →](/changelog/integrations/crewai)
-
-## Features
-
- **Drop-in Storage Backend** - Implements CrewAI's `Storage` interface for `ExternalMemory`
- **Automatic Memory Flow** - CrewAI automatically stores task outputs and retrieves relevant memories
- **Per-Agent Banks** - Optionally give each agent its own isolated memory bank
- **Reflect Tool** - Agents can explicitly reason over memories with disposition-aware synthesis
- **Simple Configuration** - Configure once, use everywhere
-
-## Installation
-
-```bash
-pip install hindsight-crewai
-```
-
-## Quick Start
-
-```python
-from hindsight_crewai import configure, HindsightStorage
-from crewai.memory.external.external_memory import ExternalMemory
-from crewai import Agent, Crew, Task
-
-configure(hindsight_api_url="http://localhost:8888")
-
-crew = Crew(
-    agents=[Agent(role="Researcher", goal="Find information", backstory="...")],
-    tasks=[Task(description="Research AI trends", expected_output="Report")],
-    external_memory=ExternalMemory(
-        storage=HindsightStorage(bank_id="my-crew")
-    ),
-)
-
-crew.kickoff()
-```
-
-That's it. CrewAI will automatically:
- **Query memories** at the start of each task
- **Store task outputs** to Hindsight after each task completes
-
-Memories persist across crew runs, so your crew learns over time.
-
-## How It Works
-
-The integration maps CrewAI's 3-method `Storage` interface to Hindsight's API:
-
-| CrewAI | Hindsight | What happens |
-|--------|-----------|--------------|
-| `save(value, metadata, agent)` | `retain(bank_id, content, ...)` | Task output is stored. Hindsight extracts facts, entities, and relationships from the raw text. |
-| `search(query, limit)` | `recall(bank_id, query, ...)` | CrewAI constructs a query from the task description. Hindsight runs semantic search, BM25, graph traversal, and reranking. |
-| `reset()` | `delete_bank(bank_id)` | Wipes the bank and optionally recreates it with its original mission. |
-
-CrewAI calls `search()` automatically at the start of each task and `save()` after each task completes.
-
-## Configuration Options
-
-```python
-from hindsight_crewai import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",  # Hindsight API URL
-    api_key="your-api-key",                     # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                               # Recall budget: "low", "mid", "high"
-    max_tokens=4096,                            # Max tokens for recall results
-    tags=["env:prod"],                          # Tags for stored memories
-    recall_tags=["scope:global"],               # Tags to filter recall
-    recall_tags_match="any",                    # Tag match: any/all/any_strict/all_strict
-    verbose=True,                               # Enable logging
-)
-```
-
-### Per-Storage Overrides
-
-Constructor arguments override global configuration:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    budget="high",
-    max_tokens=8192,
-    tags=["team:alpha"],
-)
-```
-
-## Bank Missions
-
-Set a mission to guide how Hindsight processes and organizes memories:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    mission="Track software architecture decisions, technical debt, and team preferences.",
-)
-```
-
-## Per-Agent Memory Banks
-
-Give each agent its own isolated memory bank:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    per_agent_banks=True,
-    # Researcher -> "my-crew-researcher"
-    # Writer     -> "my-crew-writer"
-)
-```
-
-Or use a custom bank resolver for full control:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    bank_resolver=lambda base, agent: f"{base}-{agent.lower()}" if agent else base,
-)
-```
-
-:::info
-When `per_agent_banks=True`, the automatic `search()` at task start queries the base bank (shared context), since CrewAI's `search()` method does not receive the agent parameter. For per-agent search isolation, create separate `HindsightStorage` instances per agent.
-:::
-
-## Reflect Tool
-
-CrewAI's storage interface only supports save/search/reset. To give agents access to Hindsight's `reflect` (disposition-aware memory synthesis), add it as a tool:
-
-```python
-from hindsight_crewai import HindsightReflectTool
-
-reflect_tool = HindsightReflectTool(
-    bank_id="my-crew",
-    budget="mid",
-    reflect_context="You are helping a software team track decisions.",
-)
-
-agent = Agent(
-    role="Analyst",
-    goal="Analyze project history",
-    backstory="...",
-    tools=[reflect_tool],
-)
-```
-
-When the agent calls this tool, it gets a synthesized, contextual answer based on all relevant memories rather than raw fact snippets.
-
-## Full Example
-
-A research crew that remembers findings across runs:
-
-```python
-from hindsight_crewai import configure, HindsightStorage, HindsightReflectTool
-from crewai.memory.external.external_memory import ExternalMemory
-from crewai import Agent, Crew, Task
-
-configure(hindsight_api_url="http://localhost:8888")
-
-storage = HindsightStorage(
-    bank_id="research-crew",
-    mission="Track technology research findings and comparisons.",
-)
-
-reflect_tool = HindsightReflectTool(bank_id="research-crew", budget="mid")
-
-researcher = Agent(
-    role="Researcher",
-    goal="Research topics, building on prior knowledge.",
-    backstory="Before starting, use hindsight_reflect to check what you already know.",
-    tools=[reflect_tool],
-)
-
-writer = Agent(
-    role="Writer",
-    goal="Write summaries incorporating prior findings.",
-    backstory="Use hindsight_reflect to recall prior research.",
-    tools=[reflect_tool],
-)
-
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[
-        Task(description="Research the benefits of Rust", expected_output="Analysis", agent=researcher),
-        Task(description="Write an executive summary", expected_output="Summary", agent=writer),
-    ],
-    external_memory=ExternalMemory(storage=storage),
-)
-
-# Run 1: researches Rust, stores findings
-crew.kickoff()
-
-# Run 2: recalls Rust research when comparing with Go
-crew.tasks[0].description = "Compare Rust with Go"
-crew.kickoff()
-```
-
-## API Reference
-
-### Configuration
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Set global connection and default settings |
-| `get_config()` | Get current configuration |
-| `reset_config()` | Reset configuration to None |
-
-### Storage
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `hindsight_api_url` | from config | Override API URL |
-| `api_key` | from config | Override API key |
-| `budget` | `"mid"` | Recall budget (low/mid/high) |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `tags` | `None` | Tags applied when storing |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `per_agent_banks` | `False` | Give each agent its own bank |
-| `bank_resolver` | `None` | Custom `(bank_id, agent) -> bank_id` |
-| `mission` | `None` | Bank mission for memory organization |
-| `verbose` | `False` | Enable verbose logging |
-
-### Reflect Tool
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `budget` | `"mid"` | Reflect budget (low/mid/high) |
-| `reflect_context` | `None` | Additional context for reasoning |
-| `hindsight_api_url` | from config | Override API URL |
-| `api_key` | from config | Override API key |
-
-## Requirements
-
- Python >= 3.10
- crewai >= 0.86.0
- A running Hindsight API server
@@ -1,177 +0,0 @@
---
-sidebar_position: 10
-title: "Hermes Agent Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Hermes Agent with Hindsight. Automatically recalls context before every LLM call and retains conversations for future sessions."
---
-
-# Hermes Agent
-
-Persistent long-term memory for [Hermes Agent](https://github.com/NousResearch/hermes-agent) using [Hindsight](https://vectorize.io/hindsight). Automatically recalls relevant context before every LLM call and retains conversations for future sessions — plus explicit retain/recall/reflect tools.
-
-## Quick Start
-
-```bash
-# 1. Install the plugin into Hermes's Python environment
-uv pip install hindsight-hermes --python $HOME/.hermes/hermes-agent/venv/bin/python
-
-# 2. Configure (choose one)
-# Option A: Config file (recommended)
-mkdir -p ~/.hindsight
-cat > ~/.hindsight/hermes.json << 'EOF'
-{
-  "hindsightApiUrl": "http://localhost:9077",
-  "bankId": "hermes"
-}
-EOF
-
-# Option B: Environment variables
-export HINDSIGHT_API_URL=http://localhost:9077
-export HINDSIGHT_BANK_ID=hermes
-
-# 3. Start Hermes — the plugin activates automatically
-hermes
-```
-
-## Features
-
- **Auto-recall** — on every turn, queries Hindsight for relevant memories and injects them into the system prompt (via `pre_llm_call` hook)
- **Auto-retain** — after every response, retains the user/assistant exchange to Hindsight (via `post_llm_call` hook)
- **Explicit tools** — `hindsight_retain`, `hindsight_recall`, `hindsight_reflect` for direct model control
- **Config file** — `~/.hindsight/hermes.json` with the same field names as openclaw and claude-code integrations
- **Zero config overhead** — env vars still work as overrides for CI/automation
-
-:::note
-The lifecycle hooks (`pre_llm_call`/`post_llm_call`) require hermes-agent with [PR #2823](https://github.com/NousResearch/hermes-agent/pull/2823) or later. On older versions, only the three tools are registered — hooks are silently skipped.
-:::
-
-## Architecture
-
-The plugin registers via Hermes's `hermes_agent.plugins` entry point system:
-
-| Component | Purpose |
-|-----------|---------|
-| `pre_llm_call` hook | **Auto-recall** — query memories, inject as ephemeral system prompt context |
-| `post_llm_call` hook | **Auto-retain** — store user/assistant exchange to Hindsight |
-| `hindsight_retain` tool | Explicit memory storage (model-initiated) |
-| `hindsight_recall` tool | Explicit memory search (model-initiated) |
-| `hindsight_reflect` tool | LLM-synthesized answer from stored memories |
-
-## Connection Modes
-
-### 1. External API (recommended for production)
-
-Connect to a running Hindsight server (cloud or self-hosted). No local LLM needed — the server handles fact extraction.
-
-```json
-{
-  "hindsightApiUrl": "https://your-hindsight-server.com",
-  "hindsightApiToken": "your-token",
-  "bankId": "hermes"
-}
-```
-
-### 2. Local Daemon
-
-If you're running `hindsight-embed` locally, point to it:
-
-```json
-{
-  "hindsightApiUrl": "http://localhost:9077",
-  "bankId": "hermes"
-}
-```
-
-Follow the [Quick Start](/developer/api/quickstart) guide to get the Hindsight API running.
-
-## Configuration
-
-All settings are in `~/.hindsight/hermes.json`. Every setting can also be overridden via environment variables (env vars take priority).
-
-### Connection & Daemon
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | — | `HINDSIGHT_API_URL` | Hindsight API URL |
-| `hindsightApiToken` | `null` | `HINDSIGHT_API_TOKEN` / `HINDSIGHT_API_KEY` | Auth token for API |
-| `apiPort` | `9077` | `HINDSIGHT_API_PORT` | Port for local Hindsight daemon |
-| `daemonIdleTimeout` | `0` | `HINDSIGHT_DAEMON_IDLE_TIMEOUT` | Seconds before idle daemon shuts down (0 = never) |
-| `embedVersion` | `"latest"` | `HINDSIGHT_EMBED_VERSION` | `hindsight-embed` version for `uvx` |
-
-### LLM Provider (daemon mode only)
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `llmProvider` | auto-detect | `HINDSIGHT_LLM_PROVIDER` | LLM provider: `openai`, `anthropic`, `gemini`, `groq`, `ollama` |
-| `llmModel` | provider default | `HINDSIGHT_LLM_MODEL` | Model override |
-
-### Memory Bank
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `bankId` | — | `HINDSIGHT_BANK_ID` | Memory bank ID |
-| `bankMission` | `""` | `HINDSIGHT_BANK_MISSION` | Agent identity/purpose for the memory bank |
-| `retainMission` | `null` | — | Custom retain mission (what to extract from conversations) |
-| `bankIdPrefix` | `""` | — | Prefix for all bank IDs |
-
-### Auto-Recall
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `true` | `HINDSIGHT_AUTO_RECALL` | Enable automatic memory recall via `pre_llm_call` hook |
-| `recallBudget` | `"mid"` | `HINDSIGHT_RECALL_BUDGET` | Recall effort: `low`, `mid`, `high` |
-| `recallMaxTokens` | `4096` | `HINDSIGHT_RECALL_MAX_TOKENS` | Max tokens in recall response |
-| `recallMaxQueryChars` | `800` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | Max chars of user message used as query |
-| `recallPromptPreamble` | see below | — | Header text injected before recalled memories |
-
-Default preamble:
-> Relevant memories from past conversations (prioritize recent when conflicting). Only use memories that are directly useful to continue this conversation; ignore the rest:
-
-### Auto-Retain
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `true` | `HINDSIGHT_AUTO_RETAIN` | Enable automatic retention via `post_llm_call` hook |
-| `retainEveryNTurns` | `1` | — | Retain every Nth turn |
-| `retainOverlapTurns` | `2` | — | Extra overlap turns for continuity |
-| `retainRoles` | `["user", "assistant"]` | — | Which message roles to retain |
-
-### Miscellaneous
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `debug` | `false` | `HINDSIGHT_DEBUG` | Enable debug logging to stderr |
-
-## Hermes Gateway (Telegram, Discord, Slack)
-
-When using Hermes in gateway mode (multi-platform messaging), the plugin works across all platforms. Hermes creates a fresh `AIAgent` per message, and the plugin's `pre_llm_call` hook ensures relevant memories are recalled for each turn regardless of platform.
-
-## Disabling Hermes's Built-in Memory
-
-Hermes has a built-in `memory` tool that saves to local markdown files. If both are active, the LLM may prefer the built-in one. Disable it:
-
-```bash
-hermes tools disable memory
-```
-
-Re-enable later with `hermes tools enable memory`.
-
-## Troubleshooting
-
-**Plugin not loading**: Verify the entry point is registered:
-```bash
-python -c "
-import importlib.metadata
-eps = importlib.metadata.entry_points(group='hermes_agent.plugins')
-print(list(eps))
-"
-```
-You should see `EntryPoint(name='hindsight', value='hindsight_hermes', ...)`.
-
-**Tools don't appear in `/tools`**: Check that `hindsightApiUrl` (or `HINDSIGHT_API_URL`) is set. The plugin silently skips registration when unconfigured.
-
-**Connection refused**: Verify the Hindsight API is running:
-```bash
-curl http://localhost:9077/health
-```
-
-**Recall returning no memories**: Memories need at least one retain cycle. Try storing a fact first, then asking about it in a new session.
@@ -1,319 +0,0 @@
---
-sidebar_position: 7
-title: "LangGraph & LangChain Persistent Memory with Hindsight"
-description: "Add long-term memory to LangGraph and LangChain agents with Hindsight. Three integration patterns — tools, nodes, and BaseStore adapter — for persistent memory across agent runs."
---
-
-# LangGraph / LangChain
-
-Persistent long-term memory for [LangGraph](https://langchain-ai.github.io/langgraph/) and [LangChain](https://python.langchain.com/) agents via Hindsight. Three integration patterns at different abstraction levels — the tools pattern works with both LangChain and LangGraph, while nodes and the BaseStore adapter are LangGraph-specific.
-
-[View Changelog →](/changelog/integrations/langgraph)
-
-## Features
-
- **Memory Tools** — retain, recall, and reflect as LangChain `@tool` functions compatible with `bind_tools()` and `ToolNode`. Works with **both LangChain and LangGraph** — no LangGraph dependency required for this pattern.
- **Graph Nodes** *(LangGraph)* — Pre-built nodes that auto-inject memories before LLM calls and auto-store after responses
- **BaseStore Adapter** *(LangGraph)* — Drop-in `BaseStore` implementation backed by Hindsight, for LangGraph's native memory patterns
- **Dynamic Banks** — Resolve bank IDs per-request from `RunnableConfig` for per-user memory
- **Async-Native** — Uses `aretain`, `arecall`, `areflect` directly — no thread-pool workarounds
-
-## Installation
-
-```bash
-pip install hindsight-langgraph
-```
-
-## Quick Start: Tools (LangChain & LangGraph)
-
-The tools pattern creates standard LangChain `@tool` functions that work with any LangChain-compatible model via `bind_tools()`. You can use them with a LangGraph agent or with plain LangChain — no LangGraph required.
-
-**With LangGraph (recommended):**
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_hindsight_tools
-from langchain_openai import ChatOpenAI
-from langgraph.prebuilt import create_react_agent
-
-client = Hindsight(base_url="http://localhost:8888")
-tools = create_hindsight_tools(client=client, bank_id="user-123")
-
-agent = create_react_agent(ChatOpenAI(model="gpt-4o"), tools=tools)
-
-result = await agent.ainvoke(
-    {"messages": [{"role": "user", "content": "Remember that I prefer dark mode"}]}
-)
-```
-
-**With plain LangChain:**
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_hindsight_tools
-from langchain_openai import ChatOpenAI
-
-client = Hindsight(base_url="http://localhost:8888")
-tools = create_hindsight_tools(client=client, bank_id="user-123")
-
-model = ChatOpenAI(model="gpt-4o").bind_tools(tools)
-response = await model.ainvoke("Remember that I prefer dark mode")
-```
-
-When using plain LangChain, you handle the tool execution loop yourself — call the model, check for `tool_calls`, execute them, and feed results back. LangGraph automates this loop for you.
-
-The agent gets three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-## Quick Start: Memory Nodes (LangGraph)
-
-Add recall and retain nodes to your graph for automatic memory injection and storage.
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_recall_node, create_retain_node
-from langgraph.graph import StateGraph, MessagesState, START, END
-
-client = Hindsight(base_url="http://localhost:8888")
-
-recall = create_recall_node(client=client, bank_id="user-123")
-retain = create_retain_node(client=client, bank_id="user-123")
-
-builder = StateGraph(MessagesState)
-builder.add_node("recall", recall)
-builder.add_node("agent", agent_node)  # your LLM node
-builder.add_node("retain", retain)
-
-builder.add_edge(START, "recall")
-builder.add_edge("recall", "agent")
-builder.add_edge("agent", "retain")
-builder.add_edge("retain", END)
-
-graph = builder.compile()
-```
-
-The recall node extracts the latest user message, searches Hindsight, and injects matching memories as a `SystemMessage`. The retain node stores human messages (optionally AI messages too) after the response.
-
-## Quick Start: BaseStore (LangGraph)
-
-Use Hindsight as a LangGraph `BaseStore` for cross-thread persistent memory with semantic search.
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import HindsightStore
-
-client = Hindsight(base_url="http://localhost:8888")
-store = HindsightStore(client=client)
-
-graph = builder.compile(checkpointer=checkpointer, store=store)
-
-# Store and search via the store API
-await store.aput(("user", "123", "prefs"), "theme", {"value": "dark mode"})
-results = await store.asearch(("user", "123", "prefs"), query="theme preference")
-```
-
-Namespace tuples are mapped to Hindsight bank IDs with `.` as separator (e.g., `("user", "123")` becomes bank `user.123`). Banks are auto-created on first access.
-
-## Dynamic Bank IDs
-
-Both nodes and the store support per-user bank resolution from `RunnableConfig`:
-
-```python
-recall = create_recall_node(client=client, bank_id_from_config="user_id")
-retain = create_retain_node(client=client, bank_id_from_config="user_id")
-
-# Bank ID resolved at runtime from config
-result = await graph.ainvoke(
-    {"messages": [{"role": "user", "content": "hello"}]},
-    config={"configurable": {"user_id": "user-456"}},
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing a client to every call, configure once:
-
-```python
-from hindsight_langgraph import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing client — uses global config
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Retain Node Options
-
-```python
-retain = create_retain_node(
-    client=client,
-    bank_id="user-123",
-    retain_human=True,    # Store human messages (default: True)
-    retain_ai=False,      # Store AI responses (default: False)
-    tags=["source:chat"], # Tags applied to stored memories
-)
-```
-
-## Recall Node Options
-
-```python
-recall = create_recall_node(
-    client=client,
-    bank_id="user-123",
-    budget="low",          # Recall budget: low/mid/high
-    max_results=10,        # Max memories injected
-    max_tokens=4096,       # Max tokens for recall
-    tags=["scope:user"],   # Filter by tags
-    tags_match="all",      # Tag match mode
-)
-```
-
-### Using `output_key` for Prompt Control
-
-By default, the recall node appends a `SystemMessage` to `messages`. Use `output_key` to write memory text to a custom state field instead, giving you full control over prompt ordering:
-
-```python
-from typing import Optional
-from langgraph.graph import MessagesState
-
-class AgentState(MessagesState):
-    memory_context: Optional[str] = None
-
-recall = create_recall_node(
-    client=client,
-    bank_id="user-123",
-    output_key="memory_context",
-)
-
-# In your agent node, read state["memory_context"] and prepend it
-# to the system prompt before calling the model.
-```
-
-## Limitations and Notes
-
-### HindsightStore
-
- **Async-only.** All sync methods (`batch`, `get`, `put`, `delete`, `search`, `list_namespaces`) raise `NotImplementedError`. Use the async variants (`abatch`, `aget`, `aput`, `adelete`, `asearch`, `alist_namespaces`) instead.
- **`get()` relies on recall.** There is no direct key lookup — the key is used as a recall query and only exact `document_id` matches are returned. Items that do not rank in the top recall results may appear missing.
- **`list_namespaces` is session-scoped.** It only tracks namespaces that have been written to via `aput()` during the current process. After a restart, `list_namespaces` returns empty even though data still exists in Hindsight.
- **`delete` is a no-op.** Calling `adelete()` logs a debug message but does not remove data from Hindsight. Hindsight's memory model is append-oriented; fact superseding is handled automatically during retain.
-
-### Memory Nodes
-
- **SystemMessage ordering.** The recall node adds a `SystemMessage` with recalled memories. Because `MessagesState` uses `add_messages` (which appends), this message appears after existing messages rather than at position 0. The message has a stable ID (`hindsight_memory_context`) so it is updated rather than duplicated across invocations. If your LLM provider requires system messages first, sort or filter messages in your agent node before passing them to the model.
-
-### Error Handling
-
- **Tools** raise `HindsightError` on failure, which surfaces to the agent as a tool error.
- **Nodes** silently log errors and return empty messages, so a Hindsight outage does not crash your graph.
-
-## API Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode (any/all/any\_strict/all\_strict) |
-| `retain_metadata` | `None` | Default metadata dict for retain operations |
-| `retain_document_id` | `None` | Default document\_id for retain (groups/upserts memories) |
-| `recall_types` | `None` | Fact types to filter (world, experience, opinion, observation) |
-| `recall_include_entities` | `False` | Include entity information in recall results |
-| `reflect_context` | `None` | Additional context for reflect operations |
-| `reflect_max_tokens` | `None` | Max tokens for reflect results (defaults to `max_tokens`) |
-| `reflect_response_schema` | `None` | JSON schema to constrain reflect output format |
-| `reflect_tags` | `None` | Tags to filter memories used in reflect (defaults to `recall_tags`) |
-| `reflect_tags_match` | `None` | Tag matching for reflect (defaults to `recall_tags_match`) |
-| `include_retain` | `True` | Include the retain (store) tool |
-| `include_recall` | `True` | Include the recall (search) tool |
-| `include_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `create_recall_node()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static bank ID (or use `bank_id_from_config`) |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall budget level |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `max_results` | `10` | Max memories to inject |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-| `bank_id_from_config` | `"user_id"` | Config key to resolve bank ID at runtime |
-| `output_key` | `None` | If set, write memory text to this state key instead of appending a SystemMessage to `messages` |
-
-### `create_retain_node()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static bank ID (or use `bank_id_from_config`) |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `tags` | `None` | Tags applied to stored memories |
-| `bank_id_from_config` | `"user_id"` | Config key to resolve bank ID at runtime |
-| `retain_human` | `True` | Store human messages |
-| `retain_ai` | `False` | Store AI responses |
-
-### `HindsightStore()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `tags` | `None` | Tags applied to all retain operations |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- langchain-core >= 0.3.0
- hindsight-client >= 0.4.0
- langgraph >= 0.3.0 *(only for nodes and store patterns — install with `pip install hindsight-langgraph[langgraph]`)*
@@ -1,349 +0,0 @@
---
-sidebar_position: 1
-title: "LiteLLM Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to any LLM application via LiteLLM and Hindsight. Universal integration — works with any model or provider with just a few lines of code."
---
-
-# LiteLLM
-
-Universal LLM memory integration via [LiteLLM](https://github.com/BerriAI/litellm). Add persistent memory to any LLM application with just a few lines of code.
-
-[View Changelog →](/changelog/integrations/litellm)
-
-## Features
-
- **Universal LLM Support** - Works with 100+ LLM providers via LiteLLM (OpenAI, Anthropic, Groq, Azure, AWS Bedrock, Google Vertex AI, and more)
- **Simple Integration** - Just configure, enable, and use `hindsight_litellm.completion()`
- **Automatic Memory Injection** - Relevant memories are injected into prompts before LLM calls
- **Automatic Conversation Storage** - Conversations are stored to Hindsight for future recall
- **Two Memory Modes** - Choose between `reflect` (synthesized context) or `recall` (raw memory retrieval)
- **Direct Memory APIs** - Query, synthesize, and store memories manually
- **Native Client Wrappers** - Alternative wrappers for OpenAI and Anthropic SDKs
-
-## Installation
-
-```bash
-pip install hindsight-litellm
-```
-
-## Quick Start
-
-```python
-import hindsight_litellm
-
-# Configure and enable memory integration
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# Use the convenience wrapper - memory is automatically injected and stored
-response = hindsight_litellm.completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What did we discuss about AI?"}]
-)
-```
-
-## How It Works
-
-When you call `completion()`, the following happens automatically:
-
-1. **Memory Retrieval** - Hindsight is queried for relevant memories based on the conversation
-2. **Prompt Injection** - Memories are injected into the system message
-3. **LLM Call** - The enriched prompt is sent to the LLM
-4. **Conversation Storage** - The conversation is stored to Hindsight for future recall
-5. **Response Returned** - You receive the response as normal
-
-## Configuration Options
-
-```python
-hindsight_litellm.configure(
-    # Required
-    hindsight_api_url="http://localhost:8888",  # Hindsight API server URL
-    bank_id="my-agent",                          # Memory bank ID
-
-    api_key="your-api-key",        # Optional API key for authentication
-
-    # Optional - Memory behavior
-    store_conversations=True,      # Store conversations after LLM calls
-    inject_memories=True,          # Inject relevant memories into prompts
-    use_reflect=False,             # Use reflect API (synthesized) vs recall (raw memories)
-    reflect_include_facts=False,   # Include source facts with reflect responses
-    max_memories=None,             # Maximum memories to inject (None = unlimited)
-    max_memory_tokens=4096,        # Maximum tokens for memory context
-    recall_budget="mid",           # Recall budget: "low", "mid", "high"
-    fact_types=["world", "agent"], # Filter fact types to inject
-
-    # Optional - Bank Configuration
-    bank_name="My Agent",          # Human-readable display name for the memory bank
-    mission="This agent...",       # Instructions guiding what Hindsight should remember
-
-    # Optional - Advanced
-    injection_mode="system_message",  # or "prepend_user"
-    excluded_models=["gpt-3.5*"],     # Exclude certain models
-    verbose=True,                     # Enable verbose logging and debug info
-)
-```
-
-### Bank Configuration
-
-The `mission` and `bank_name` parameters configure the memory bank itself. When provided, `configure()` will automatically create or update the bank with these settings.
-
-```python
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="support-router",
-    bank_name="Customer Support Router",
-    mission="""You're a customer support router - keep track of which types of issues
-    should go to which teams (billing, technical, sales), customer preferences for
-    communication channels, and past issue resolutions.""",
-)
-```
-
-### Memory Modes: Reflect vs Recall
-
- **Recall mode** (`use_reflect=False`, default): Retrieves raw memory facts and injects them as a numbered list. Best when you need precise, individual memories.
- **Reflect mode** (`use_reflect=True`): Synthesizes memories into a coherent context paragraph. Best for natural, conversational memory context.
-
-```python
-# Recall mode - raw memories
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=False,  # Default
-)
-# Injects: "1. [WORLD] User prefers Python\n2. [MENTAL MODEL] User prefers simple code..."
-
-# Reflect mode - synthesized context
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=True,
-)
-# Injects: "Based on previous conversations, the user is a Python developer who..."
-```
-
-## Multi-Provider Support
-
-Works with any LiteLLM-supported provider:
-
-```python
-import hindsight_litellm
-
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# OpenAI
-hindsight_litellm.completion(model="gpt-4o", messages=[...])
-
-# Anthropic
-hindsight_litellm.completion(model="claude-3-5-sonnet-20241022", messages=[...])
-
-# Groq
-hindsight_litellm.completion(model="groq/llama-3.1-70b-versatile", messages=[...])
-
-# Azure OpenAI
-hindsight_litellm.completion(model="azure/gpt-4", messages=[...])
-
-# AWS Bedrock
-hindsight_litellm.completion(model="bedrock/anthropic.claude-3", messages=[...])
-
-# Google Vertex AI
-hindsight_litellm.completion(model="vertex_ai/gemini-pro", messages=[...])
-```
-
-## Direct Memory APIs
-
-### Recall - Query raw memories
-
-```python
-from hindsight_litellm import configure, recall
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-memories = recall("what projects am I working on?", budget="mid")
-for m in memories:
-    print(f"- [{m.fact_type}] {m.text}")
-```
-
-### Reflect - Get synthesized context
-
-```python
-from hindsight_litellm import configure, reflect
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = reflect("what do you know about the user's preferences?")
-print(result.text)
-```
-
-### Retain - Store memories
-
-```python
-from hindsight_litellm import configure, retain
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = retain(
-    content="User mentioned they're working on a machine learning project",
-    context="Discussion about current projects",
-)
-```
-
-### Async APIs
-
-```python
-from hindsight_litellm import arecall, areflect, aretain
-
-# Async versions of all memory APIs
-memories = await arecall("what do you know about me?")
-context = await areflect("summarize user preferences")
-result = await aretain(content="New information to remember")
-```
-
-## Native Client Wrappers
-
-Alternative to LiteLLM callbacks for direct SDK integration.
-
-### OpenAI Wrapper
-
-```python
-from openai import OpenAI
-from hindsight_litellm import wrap_openai
-
-client = OpenAI()
-wrapped = wrap_openai(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.chat.completions.create(
-    model="gpt-4",
-    messages=[{"role": "user", "content": "What do you know about me?"}]
-)
-```
-
-### Anthropic Wrapper
-
-```python
-from anthropic import Anthropic
-from hindsight_litellm import wrap_anthropic
-
-client = Anthropic()
-wrapped = wrap_anthropic(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.messages.create(
-    model="claude-3-5-sonnet-20241022",
-    max_tokens=1024,
-    messages=[{"role": "user", "content": "Hello!"}]
-)
-```
-
-## Debug Mode
-
-When `verbose=True`, you can inspect exactly what memories are being injected:
-
-```python
-from hindsight_litellm import configure, enable, completion, get_last_injection_debug
-
-configure(
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-    verbose=True,
-)
-enable()
-
-response = completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What's my favorite color?"}]
-)
-
-# Inspect what was injected
-debug = get_last_injection_debug()
-if debug:
-    print(f"Mode: {debug.mode}")           # "reflect" or "recall"
-    print(f"Injected: {debug.injected}")   # True/False
-    print(f"Results: {debug.results_count}")
-    print(f"Memory context:\n{debug.memory_context}")
-```
-
-## Context Manager
-
-```python
-from hindsight_litellm import hindsight_memory
-import litellm
-
-with hindsight_memory(bank_id="user-123"):
-    response = litellm.completion(model="gpt-4", messages=[...])
-# Memory integration automatically disabled after context
-```
-
-## Disabling and Cleanup
-
-```python
-from hindsight_litellm import disable, cleanup
-
-# Temporarily disable memory integration
-disable()
-
-# Clean up all resources (call when shutting down)
-cleanup()
-```
-
-## API Reference
-
-### Main Functions
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Configure global Hindsight settings |
-| `enable()` | Enable memory integration with LiteLLM |
-| `disable()` | Disable memory integration |
-| `is_enabled()` | Check if memory integration is enabled |
-| `cleanup()` | Clean up all resources |
-
-### Configuration Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_config()` | Get current configuration |
-| `is_configured()` | Check if Hindsight is configured |
-| `reset_config()` | Reset configuration to defaults |
-
-### Memory Functions
-
-| Function | Description |
-|----------|-------------|
-| `recall(query, ...)` | Synchronously query raw memories |
-| `arecall(query, ...)` | Asynchronously query raw memories |
-| `reflect(query, ...)` | Synchronously get synthesized memory context |
-| `areflect(query, ...)` | Asynchronously get synthesized memory context |
-| `retain(content, ...)` | Synchronously store a memory |
-| `aretain(content, ...)` | Asynchronously store a memory |
-
-### Debug Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_last_injection_debug()` | Get debug info from last memory injection |
-| `clear_injection_debug()` | Clear stored debug info |
-
-### Client Wrappers
-
-| Function | Description |
-|----------|-------------|
-| `wrap_openai(client, ...)` | Wrap OpenAI client with memory |
-| `wrap_anthropic(client, ...)` | Wrap Anthropic client with memory |
-
-## Requirements
-
- Python >= 3.10
- litellm >= 1.40.0
- A running Hindsight API server
@@ -1,251 +0,0 @@
---
-sidebar_position: 8
-title: "LlamaIndex Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to LlamaIndex agents with Hindsight. Supports agent-driven tools (HindsightToolSpec) and automatic memory via the BaseMemory interface."
---
-
-# LlamaIndex
-
-Persistent long-term memory for [LlamaIndex](https://docs.llamaindex.ai/) agents via Hindsight. The `hindsight-llamaindex` package provides two complementary patterns:
-
- **`HindsightToolSpec`** — Agent-driven memory tools (retain/recall/reflect)
- **`HindsightMemory`** — Automatic memory via LlamaIndex's `BaseMemory` interface
-
-## Installation
-
-```bash
-pip install hindsight-llamaindex
-```
-
---
-
-## Automatic Memory (BaseMemory)
-
-The simplest way to add Hindsight memory to a LlamaIndex agent. Messages are automatically stored on each turn, and relevant memories are recalled and injected as context.
-
-```python
-import asyncio
-from hindsight_client import Hindsight
-from hindsight_llamaindex import HindsightMemory
-from llama_index.core.agent import ReActAgent
-from llama_index.llms.openai import OpenAI
-
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-
-    memory = HindsightMemory.from_client(
-        client=client,
-        bank_id="user-123",
-        mission="Track user preferences and project context",
-    )
-
-    agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o"))
-    response = await agent.run("Remember that I prefer dark mode", memory=memory)
-    print(response)
-
-asyncio.run(main())
-```
-
-### How It Works
-
-| Event | What Happens |
-|-------|-------------|
-| Agent receives input | `aget(input)` recalls relevant memories from Hindsight, prepends as system message |
-| Agent produces output | `aput(message)` retains the message to Hindsight for future recall |
-| New session starts | Previous memories are available via recall; local chat buffer starts empty |
-
-### `HindsightMemory.from_client()`
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `client` | `Hindsight` | *required* | Hindsight client instance |
-| `bank_id` | `str` | *required* | Memory bank ID |
-| `mission` | `str` | `None` | Bank mission — auto-creates bank on first use |
-| `context` | `str` | `"llamaindex"` | Source label for retain operations |
-| `budget` | `str` | `"mid"` | Recall budget level |
-| `max_tokens` | `int` | `4096` | Max recall tokens |
-| `tags` | `list[str]` | `None` | Tags for retain operations |
-| `recall_tags` | `list[str]` | `None` | Tags to filter recall |
-| `recall_tags_match` | `str` | `"any"` | Tag matching mode |
-| `system_prompt` | `str` | *(built-in)* | Template for memory system message. Must contain `{memories}` |
-| `chat_history_limit` | `int` | `100` | Max messages in local buffer |
-
-Also available: `HindsightMemory.from_url(hindsight_api_url, bank_id, ...)` for creating without a pre-built client.
-
---
-
-## Agent-Driven Tools (BaseToolSpec)
-
-For explicit control, expose retain/recall/reflect as tools the agent can choose to call.
-
-### Quick Start: Tool Spec
-
-```python
-import asyncio
-from hindsight_client import Hindsight
-from hindsight_llamaindex import HindsightToolSpec
-from llama_index.llms.openai import OpenAI
-from llama_index.core.agent import ReActAgent
-
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-
-    spec = HindsightToolSpec(
-        client=client,
-        bank_id="user-123",
-        mission="Track user preferences",
-    )
-    tools = spec.to_tool_list()
-
-    agent = ReActAgent(tools=tools, llm=OpenAI(model="gpt-4o"))
-    response = await agent.run("Remember that I prefer dark mode")
-    print(response)
-
-asyncio.run(main())
-```
-
-### Quick Start: Factory Function
-
-```python
-from hindsight_llamaindex import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    mission="Track user preferences",
-)
-```
-
-### Selecting Tools
-
-```python
-# Via to_tool_list()
-tools = spec.to_tool_list(spec_functions=["recall_memory", "reflect_on_memory"])
-
-# Via factory flags
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,
-)
-```
-
-### Configuration
-
-Set defaults via `configure()`, override per-call:
-
-```python
-from hindsight_llamaindex import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",  # or set HINDSIGHT_API_KEY env var
-    budget="mid",
-    tags=["source:llamaindex"],
-    context="my-app",
-    mission="Track user preferences",
-)
-
-# Now create tools without passing client/url
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-### `HindsightToolSpec()`
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `bank_id` | `str` | *required* | Hindsight memory bank to operate on |
-| `client` | `Hindsight` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `str` | `None` | API URL (used if no client provided) |
-| `api_key` | `str` | `None` | API key (used if no client provided) |
-| `budget` | `str` | `None` → `"mid"` | Recall/reflect budget: `low`, `mid`, `high` |
-| `max_tokens` | `int` | `None` → `4096` | Max tokens for recall results |
-| `tags` | `list[str]` | `None` | Tags applied when storing memories |
-| `recall_tags` | `list[str]` | `None` | Tags to filter recall results |
-| `recall_tags_match` | `str` | `None` → `"any"` | Tag matching: `any`, `all`, `any_strict`, `all_strict` |
-| `retain_metadata` | `dict[str, str]` | `None` | Default metadata for retain operations |
-| `retain_document_id` | `str` | `None` | Document ID for retain. Auto-generates `{session}-{timestamp}` if not set |
-| `retain_context` | `str` | `"llamaindex"` | Source label for retain operations |
-| `recall_types` | `list[str]` | `None` | Fact types: `world`, `experience`, `opinion`, `observation` |
-| `recall_include_entities` | `bool` | `False` | Include entity info in recall results |
-| `reflect_context` | `str` | `None` | Additional context for reflect |
-| `reflect_max_tokens` | `int` | `None` | Max tokens for reflect (defaults to `max_tokens`) |
-| `reflect_response_schema` | `dict` | `None` | JSON schema to constrain reflect output |
-| `reflect_tags` | `list[str]` | `None` | Tags for reflect (defaults to `recall_tags`) |
-| `reflect_tags_match` | `str` | `None` | Tag matching for reflect (defaults to `recall_tags_match`) |
-| `mission` | `str` | `None` | Bank mission — auto-creates bank on first use |
-
---
-
-## Production Patterns
-
-### Bank Mission
-
-Set a mission to give the memory engine context for fact extraction:
-
-```python
-# Tools
-spec = HindsightToolSpec(
-    client=client,
-    bank_id="user-123",
-    mission="Track user coding preferences, project context, and technical decisions",
-)
-
-# Memory
-memory = HindsightMemory.from_client(
-    client=client,
-    bank_id="user-123",
-    mission="Track user coding preferences, project context, and technical decisions",
-)
-```
-
-The bank is created automatically on first use. If it already exists, creation is silently skipped.
-
-### Memory Scoping with Tags
-
-```python
-spec = HindsightToolSpec(
-    client=client,
-    bank_id="user-123",
-    tags=["source:chat", "session:abc"],        # applied to all retains
-    recall_tags=["source:chat"],                 # filter recalls to chat memories
-    recall_tags_match="any",
-)
-```
-
-### Error Handling
-
-Both patterns handle errors gracefully — operations are logged and return friendly messages instead of raising exceptions. Agents continue functioning even if memory is unavailable.
-
-### Combining Tools + Memory
-
-Use both patterns together for maximum flexibility:
-
-```python
-from hindsight_llamaindex import create_hindsight_tools, HindsightMemory
-
-# Automatic memory for context enrichment
-memory = HindsightMemory.from_client(client=client, bank_id="user-123")
-
-# Explicit tools for agent-driven reflect
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=False,   # memory handles retain automatically
-    include_recall=False,   # memory handles recall automatically
-    include_reflect=True,   # agent can still explicitly reflect
-)
-
-agent = ReActAgent(tools=tools, llm=llm)
-
-# Pass memory to run()
-response = await agent.run("What should I prioritize?", memory=memory)
-```
-
-## Requirements
-
- Python 3.10+
- `llama-index-core >= 0.11.0`
- `hindsight-client >= 0.4.0`
@@ -1,176 +0,0 @@
---
-sidebar_position: 2
-title: "Hindsight Local MCP Server | Persistent Memory for Claude"
-description: "Run Hindsight as a local MCP server with embedded PostgreSQL — no external setup required. Ideal for Claude Code and Claude Desktop for long-term memory across conversations."
---
-
-# Local MCP Server
-
-Hindsight provides a local MCP server that runs entirely on your machine with an embedded PostgreSQL database. No external server or database setup required.
-
-This is ideal for:
- **Personal use with Claude Code / Claude Desktop** — Give Claude long-term memory across conversations
- **Development and testing** — Quick setup without infrastructure
- **Privacy-focused setups** — All data stays on your machine
-
-## How It Works
-
-Running `hindsight-local-mcp` starts the full Hindsight API on `localhost:8888` with an embedded PostgreSQL database (pg0). You then connect your MCP client to it over HTTP.
-
- Starts an embedded PostgreSQL (pg0) automatically
- Runs database migrations on startup
- Exposes the full MCP endpoint at `http://localhost:8888/mcp/`
- Data persists in `~/.pg0/hindsight-mcp/` across restarts
-
-## Setup
-
-### 1. Start the server
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... uvx --from hindsight-api hindsight-local-mcp
-```
-
-Or with Ollama (no API key needed):
-
-```bash
-HINDSIGHT_API_LLM_PROVIDER=ollama HINDSIGHT_API_LLM_MODEL=llama3.2 uvx --from hindsight-api hindsight-local-mcp
-```
-
-### 2. Configure your MCP client
-
-**Claude Code:**
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/
-```
-
-**Other MCP clients** — add an HTTP transport entry pointing to `http://localhost:8888/mcp/`.
-
-## Bank Modes
-
-The local server supports the same two modes as the hosted API:
-
-### Multi-bank mode (default)
-
-Use `http://localhost:8888/mcp/` — exposes all tools including bank management. Bank is selected per-request via the `bank_id` tool parameter or the `X-Bank-Id` header.
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/
-```
-
-### Single-bank mode
-
-Use `http://localhost:8888/mcp/<bank-id>/` — pins all tools to one bank, no `bank_id` parameter needed. This replaces the old `HINDSIGHT_API_MCP_LOCAL_BANK_ID` env var.
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/my-bank/
-```
-
-## Available Tools
-
-The local server exposes the full tool set (29 tools in multi-bank mode, 26 in single-bank mode):
-
-**Core Memory**
-
-| Tool | Description |
-|------|-------------|
-| `retain` | Store information to long-term memory with optional tags, metadata, and document association |
-| `recall` | Search memories with natural language, configurable budget, type filters, and tag filters |
-| `reflect` | Synthesize memories into a reasoned answer with optional structured output |
-
-**Mental Models**
-
-| Tool | Description |
-|------|-------------|
-| `list_mental_models` | List pinned reflections for a bank |
-| `get_mental_model` | Get a specific mental model |
-| `create_mental_model` | Create a new mental model with optional auto-refresh trigger |
-| `update_mental_model` | Update a mental model's metadata |
-| `delete_mental_model` | Delete a mental model |
-| `refresh_mental_model` | Regenerate a mental model's content |
-
-**Directives**
-
-| Tool | Description |
-|------|-------------|
-| `list_directives` | List directives that guide memory processing |
-| `create_directive` | Create a new directive |
-| `delete_directive` | Delete a directive |
-
-**Memory Browsing**
-
-| Tool | Description |
-|------|-------------|
-| `list_memories` | Browse memories with filtering and pagination |
-| `get_memory` | Get a specific memory by ID |
-| `delete_memory` | Delete a specific memory |
-
-**Documents**
-
-| Tool | Description |
-|------|-------------|
-| `list_documents` | List ingested documents |
-| `get_document` | Get a specific document |
-| `delete_document` | Delete a document and its linked memories |
-
-**Operations**
-
-| Tool | Description |
-|------|-------------|
-| `list_operations` | List async operations with status filtering |
-| `get_operation` | Check operation status and progress |
-| `cancel_operation` | Cancel a pending or running operation |
-
-**Tags & Bank Management**
-
-| Tool | Description |
-|------|-------------|
-| `list_tags` | List unique tags used in a bank |
-| `get_bank` | Get bank profile (name, mission, disposition) |
-| `get_bank_stats` | Get bank statistics (multi-bank only) |
-| `update_bank` | Update bank name or mission |
-| `delete_bank` | Delete an entire bank and all its data |
-| `clear_memories` | Clear memories without deleting the bank |
-| `list_banks` | List all memory banks (multi-bank only) |
-| `create_bank` | Create or configure a memory bank (multi-bank only) |
-
-For detailed parameter documentation, see the [MCP Server reference](/developer/mcp-server#available-tools).
-
-## Environment Variables
-
-All standard [Hindsight configuration variables](/developer/configuration) are supported. Key ones for local use:
-
-| Variable | Required | Default | Description |
-|----------|----------|---------|-------------|
-| `HINDSIGHT_API_LLM_API_KEY` | Yes* | — | API key for your LLM provider |
-| `HINDSIGHT_API_LLM_PROVIDER` | No | `openai` | LLM provider (`openai`, `anthropic`, `ollama`, etc.) |
-| `HINDSIGHT_API_LLM_MODEL` | No | `gpt-4o-mini` | Model name |
-| `HINDSIGHT_API_DATABASE_URL` | No | `pg0://hindsight-mcp` | Override the database URL |
-| `HINDSIGHT_API_PORT` | No | `8888` | Port to listen on |
-| `HINDSIGHT_API_LOG_LEVEL` | No | `info` | Log level |
-
-*Not required when using a local provider like Ollama.
-
-## Troubleshooting
-
-### Slow first startup
-
-The first startup downloads the local embedding model (~100MB) and initializes the database. Subsequent starts are faster.
-
-### Port already in use
-
-Set a different port:
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... HINDSIGHT_API_PORT=9000 uvx --from hindsight-api hindsight-local-mcp
-```
-
-Then update your MCP client URL to `http://localhost:9000/mcp/`.
-
-### Checking logs
-
-Set `HINDSIGHT_API_LOG_LEVEL=debug` for verbose output:
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... HINDSIGHT_API_LOG_LEVEL=debug uvx --from hindsight-api hindsight-local-mcp
-```
@@ -1,250 +0,0 @@
---
-sidebar_position: 5
-title: "NemoClaw Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to NemoClaw sandboxed agents with Hindsight. One command adds automated memory extraction and auto-recall to any NemoClaw sandbox — no code changes required."
---
-
-# NemoClaw
-
-Persistent memory for [NemoClaw](https://nemoclaw.ai) sandboxed agents using [Hindsight](https://hindsight.vectorize.io).
-
-NemoClaw runs [OpenClaw](https://openclaw.ai) inside an OpenShell sandbox with controlled filesystem, process, and network egress policies. The `hindsight-nemoclaw` package automates adding Hindsight memory to a sandbox in one command — no code changes required.
-
-[View Changelog →](/changelog/integrations/nemoclaw)
-
-## Quick Start
-
-```bash
-npx @vectorize-io/hindsight-nemoclaw setup \
-  --sandbox my-assistant \
-  --api-url https://api.hindsight.vectorize.io \
-  --api-token <your-api-key> \
-  --bank-prefix my-sandbox
-```
-
-Get an API key at [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup).
-
-You'll see output like:
-
-```
-[0] Preflight checks...
-  ✓ openshell found
-  ✓ openclaw found
-
-[1] Installing @vectorize-io/hindsight-openclaw plugin...
-  ✓ Plugin installed
-
-[2] Configuring plugin in ~/.openclaw/openclaw.json...
-  ✓ Plugin config written (bank: my-sandbox-openclaw)
-
-[3] Applying Hindsight network policy to sandbox "my-assistant"...
-  ✓ Policy version 2 submitted
-  ✓ Policy version 2 loaded (active version: 2)
-
-[4] Restarting OpenClaw gateway...
-  ✓ Gateway restarted
-
-✓ Setup complete!
-```
-
-## How It Works
-
-### The sandbox problem
-
-OpenShell enforces strict network egress — every outbound endpoint must be explicitly permitted in the sandbox policy. By default, the Hindsight API (`api.hindsight.vectorize.io`) is not in that list.
-
-The `hindsight-openclaw` plugin supports **external API mode**, where it skips the local daemon entirely and makes direct HTTPS calls to Hindsight Cloud. This is the natural fit for sandboxed environments: the plugin becomes a thin HTTP client, and the only sandbox change needed is one egress rule.
-
-### What the setup command does
-
-1. **Preflight** — verifies `openshell` and `openclaw` are installed
-2. **Install plugin** — runs `openclaw plugins install @vectorize-io/hindsight-openclaw`
-3. **Configure plugin** — writes external API mode config to `~/.openclaw/openclaw.json`
-4. **Apply policy** — reads the current sandbox policy, merges the Hindsight egress block, and re-applies via `openshell policy set`
-5. **Restart gateway** — runs `openclaw gateway restart`
-
-### Memory flow
-
-Once set up, the `hindsight-openclaw` plugin hooks into the OpenClaw gateway lifecycle:
-
- **`before_agent_start`** — recalls relevant memories from past sessions and injects them into context
- **`agent_end`** — retains the conversation to the Hindsight memory bank
-
-The sandbox doesn't interfere with either step — it sees the Hindsight calls as normal HTTPS egress to a permitted endpoint.
-
-## CLI Reference
-
-```
-hindsight-nemoclaw setup [options]
-
-Options:
-  --sandbox <name>       NemoClaw sandbox name (required)
-  --api-url <url>        Hindsight API URL (required)
-  --api-token <token>    Hindsight API token (required)
-  --bank-prefix <prefix> Memory bank prefix (default: "nemoclaw")
-  --skip-policy          Skip sandbox network policy update
-  --skip-plugin-install  Skip openclaw plugin installation
-  --dry-run              Preview changes without applying
-  --help                 Show help
-```
-
-Use `--dry-run` to preview all changes before applying anything. Use `--skip-policy` if you manage sandbox policies manually.
-
-## Manual Setup
-
-If you prefer to apply the steps yourself instead of using the CLI:
-
-### 1. Install the plugin
-
-```bash
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### 2. Configure `~/.openclaw/openclaw.json`
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "hindsightApiUrl": "https://api.hindsight.vectorize.io",
-          "hindsightApiToken": "<your-api-key>",
-          "llmProvider": "claude-code",
-          "dynamicBankId": false,
-          "bankIdPrefix": "my-sandbox"
-        }
-      }
-    }
-  }
-}
-```
-
-`llmProvider: "claude-code"` uses the Claude Code process already present in the sandbox — no additional API key needed.
-
-### 3. Add the Hindsight network policy
-
-`openshell policy set` replaces the entire policy document. Export your current policy first, add the Hindsight block, then re-apply:
-
-```yaml
-network_policies:
-  hindsight:
-    name: hindsight
-    endpoints:
-      - host: api.hindsight.vectorize.io
-        port: 443
-        protocol: rest
-        tls: terminate
-        enforcement: enforce
-        rules:
-          - allow:
-              method: GET
-              path: /**
-          - allow:
-              method: POST
-              path: /**
-          - allow:
-              method: PUT
-              path: /**
-    binaries:
-      - path: /usr/local/bin/openclaw
-```
-
-```bash
-openshell policy set my-sandbox --policy /path/to/full-policy.yaml --wait
-openclaw gateway restart
-```
-
-## Configuration Options
-
-| Option | Type | Default | Description |
-|---|---|---|---|
-| `hindsightApiUrl` | string | — | Hindsight API base URL |
-| `hindsightApiToken` | string | — | API token for authentication |
-| `llmProvider` | string | auto-detect | LLM provider for memory extraction |
-| `dynamicBankId` | boolean | `false` | Isolate memory per user (`true`) or share across sessions (`false`) |
-| `bankIdPrefix` | string | `"nemoclaw"` | Prefix for the memory bank name |
-
-### Bank naming
-
-When `dynamicBankId: false`, all sessions write to a single bank named `{bankIdPrefix}-openclaw`. When `dynamicBankId: true`, each user gets an isolated bank — useful for multi-tenant deployments.
-
-## Verifying It Works
-
-After setup, check the gateway logs:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-```
-
-On startup you should see:
-
-```
-[Hindsight] Plugin loaded successfully
-[Hindsight] ✓ Using external API: https://api.hindsight.vectorize.io
-[Hindsight] External API health: {"status":"healthy","database":"connected"}
-[Hindsight] Default bank: my-sandbox-openclaw
-[Hindsight] ✓ Ready (external API mode)
-```
-
-After a conversation:
-
-```
-[Hindsight] before_agent_start - bank: my-sandbox-openclaw, channel: undefined/webchat
-[Hindsight Hook] agent_end triggered - bank: my-sandbox-openclaw
-[Hindsight] Retained 6 messages to bank my-sandbox-openclaw for session agent:main:...
-```
-
-## Pitfalls
-
-### Policy replacement is full-document
-
-`openshell policy set` replaces the entire policy document. The `hindsight-nemoclaw setup` command handles this automatically. If you're applying manually, export the current policy first so existing rules aren't lost.
-
-### LaunchAgent can't follow symlinks on macOS
-
-On macOS, the OpenClaw gateway runs as a LaunchAgent under a restricted security context. `openclaw plugins install --link` creates a symlink the LaunchAgent can't follow — the setup command installs as a copy instead. If you see `EPERM: operation not permitted, scandir` in gateway logs, this is the cause.
-
-### Memory retention is asynchronous
-
-Fact extraction and entity resolution happen in the background after `retain`. If you open a new session immediately after closing one, the most recent memories may not be indexed yet — typically a few seconds.
-
-### Binary-scoped egress
-
-The `binaries` field in the network policy restricts the egress rule to a specific executable path. If OpenClaw updates and the binary path changes, the rule silently stops working. Check your binary path after upgrades.
-
-## Troubleshooting
-
-### Plugin not loading
-
-```bash
-openclaw plugins list | grep hindsight
-# Should show: ✓ enabled │ Hindsight Memory │ ...
-
-# Reinstall
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### Egress blocked
-
-If calls to `api.hindsight.vectorize.io` are being blocked, check the active sandbox policy:
-
-```bash
-openshell sandbox get my-assistant
-```
-
-Verify the `hindsight` block is present and the `binaries` path matches your OpenClaw binary:
-
-```bash
-which openclaw
-```
-
-### External API not connecting
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# If you see daemon startup messages instead of "Using external API",
-# the plugin config isn't being read — check ~/.openclaw/openclaw.json
-```
@@ -1,374 +0,0 @@
---
-sidebar_position: 4
-title: "OpenClaw Persistent Memory with Hindsight | Plugin Integration"
-description: "Add persistent, automated memory to your OpenClaw agent with Hindsight. Local-first, open source — one plugin install replaces built-in memory with structured knowledge extraction and auto-recall."
---
-
-# OpenClaw
-
-Local, long term memory for [OpenClaw](https://openclaw.ai) agents using [Hindsight](https://vectorize.io/hindsight).
-
-This plugin integrates [hindsight-embed](https://vectorize.io/hindsight/cli), a standalone daemon that bundles Hindsight's memory engine (API + PostgreSQL) into a single command. Everything runs locally on your machine, reuses the LLM you're already paying for, and costs nothing extra.
-
-[View Changelog →](/changelog/integrations/openclaw)
-
-## Quick Start
-
-**Step 1: Set up LLM for memory extraction**
-
-Choose one provider and set its API key:
-
-```bash
-# Option A: OpenAI
-export OPENAI_API_KEY="sk-your-key"
-
-# Option B: Anthropic
-export ANTHROPIC_API_KEY="your-key"
-
-# Option C: Gemini
-export GEMINI_API_KEY="your-key"
-
-# Option D: Groq
-export GROQ_API_KEY="your-key"
-
-# Option E: Claude Code (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=claude-code
-
-# Option F: OpenAI Codex (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=openai-codex
-```
-
-**Step 2: Install the plugin**
-
-```bash
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-**Step 3: Start OpenClaw**
-
-```bash
-openclaw gateway
-```
-
-The plugin will automatically:
- Start a local Hindsight daemon (port 9077)
- Capture conversations after each turn
- Inject relevant memories before agent responses
-
-**Important:** The LLM you configure above is **only for memory extraction** (background processing). Your main OpenClaw agent can use any model you configure separately.
-
-## How It Works
-
-**Auto-Capture:** Every conversation is automatically stored after each turn. Facts, entities, and relationships are extracted in the background.
-
-**Auto-Recall:** Before each agent response, relevant memories are automatically injected into the context (up to 1024 tokens). The agent uses past context without needing to call tools.
-
-**Feedback Loop Prevention:** The plugin automatically strips injected memory tags (`<hindsight_memories>`) before storing conversations. This prevents recalled memories from being re-extracted as new facts, which would cause exponential memory growth and duplicate entries.
-
-Traditional memory systems give agents a `search_memory` tool - but models don't use it consistently. Auto-recall solves this by injecting memories automatically before every turn.
-
-## Configuration
-
-### Plugin Settings
-
-Optional settings in `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "apiPort": 9077,
-          "daemonIdleTimeout": 0,
-          "embedVersion": "latest"
-        }
-      }
-    }
-  }
-}
-```
-
-**Options:**
- `apiPort` - Port for the openclaw profile daemon (default: `9077`)
- `daemonIdleTimeout` - Seconds before daemon shuts down from inactivity (default: `0` = never)
- `embedVersion` - hindsight-embed version (default: `"latest"`)
- `bankMission` - Agent identity/purpose stored on the memory bank. Helps the memory engine understand context for better fact extraction during retain. Set once per bank on first use — not a recall prompt.
- `dynamicBankId` - Enable per-context memory banks (default: `true`)
- `bankIdPrefix` - Optional prefix for bank IDs (e.g. `"prod"` → `"prod-slack-C123"`)
- `dynamicBankGranularity` - Fields used to derive bank ID: `agent`, `channel`, `user`, `provider` (default: `["agent", "channel", "user"]`)
- `excludeProviders` - Message providers to skip for recall/retain (e.g. `["slack"]`, `["telegram"]`, `["discord"]`)
- `autoRecall` - Auto-inject memories before each turn (default: `true`). Set to `false` when the agent has its own recall tool.
- `autoRetain` - Auto-retain conversations after each turn (default: `true`)
- `retainRoles` - Which message roles to retain (default: `["user", "assistant"]`). Options: `user`, `assistant`, `system`, `tool`
- `recallBudget` - Recall effort: `"low"`, `"mid"`, or `"high"` (default: `"mid"`). Higher budgets use more retrieval strategies for better results.
- `recallMaxTokens` - Max tokens for recall response (default: `1024`). Controls how much memory context is injected per turn.
- `recallTopK` - Max number of memories to inject per turn (default: unlimited).
- `recallTypes` - Memory types to recall (default: `["world", "experience"]`). Options: `world`, `experience`, `observation`.
- `recallContextTurns` - Number of prior user turns to include in the recall query (default: `1`).
- `recallMaxQueryChars` - Max characters for the composed recall query (default: `800`).
- `recallPromptPreamble` - Custom preamble text placed above recalled memories. Overrides the built-in guidance text.
- `recallInjectionPosition` - Where to inject recalled memories: `"prepend"` (default), `"append"`, or `"user"`. Use `"append"` to preserve prompt caching with large static system prompts. Use `"user"` to inject before the user message instead of in the system prompt.
- `recallRoles` - Which message roles to include when composing the contextual recall query (default: `["user", "assistant"]`).
- `retainEveryNTurns` - Retain every Nth turn (default: `1` = every turn). Values > 1 enable chunked retention.
- `retainOverlapTurns` - Extra prior turns included when chunked retention fires (default: `0`).
- `debug` - Enable debug logging (default: `false`).
-
-### Memory Isolation
-
-The plugin creates separate memory banks based on conversation context. By default, banks are derived from the `agent`, `channel`, and `user` fields — so each unique combination gets its own isolated memory store.
-
-You can customize which fields are used for bank segmentation with `dynamicBankGranularity`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "dynamicBankGranularity": ["provider", "user"]
-        }
-      }
-    }
-  }
-}
-```
-
-In this example, memories are isolated per provider + user, meaning the same user shares memories across all channels within a provider.
-
-Available isolation fields:
- `agent` - The agent/bot identity
- `channel` - The channel or conversation ID
- `user` - The user interacting with the agent
- `provider` - The message provider (e.g. Slack, Discord)
-
-Use `bankIdPrefix` to namespace bank IDs across environments (e.g. `"prod"`, `"staging"`). Set `dynamicBankId` to `false` to use a single shared bank for all conversations.
-
-### Retention Controls
-
-By default, the plugin retains `user` and `assistant` messages after each turn. You can customize this behavior:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "autoRetain": true,
-          "retainRoles": ["user", "assistant", "system"]
-        }
-      }
-    }
-  }
-}
-```
-
- `autoRetain` - Set to `false` to disable automatic retention entirely (useful if you handle retention yourself)
- `retainRoles` - Controls which message roles are included in the retained transcript. Only messages from the last user message onward are retained each turn, preventing duplicate storage.
-
-### LLM Configuration
-
-The plugin auto-detects your LLM provider from these environment variables:
-
-| Provider | Env Var | Notes |
-|----------|---------|-------|
-| OpenAI | `OPENAI_API_KEY` | |
-| Anthropic | `ANTHROPIC_API_KEY` | |
-| Gemini | `GEMINI_API_KEY` | |
-| Groq | `GROQ_API_KEY` | |
-| Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | No API key needed |
-| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | No API key needed |
-
-The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_API_LLM_MODEL`.
-
-**Override with explicit config:**
-
-```bash
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_API_KEY=sk-your-key
-
-# Optional: custom base URL (OpenRouter, Azure, vLLM, etc.)
-export HINDSIGHT_API_LLM_BASE_URL=https://openrouter.ai/api/v1
-```
-
-**Example: Free OpenRouter model**
-
-```bash
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_MODEL=xiaomi/mimo-v2-flash  # FREE!
-export HINDSIGHT_API_LLM_API_KEY=sk-or-v1-your-openrouter-key
-export HINDSIGHT_API_LLM_BASE_URL=https://openrouter.ai/api/v1
-```
-
-### External API (Advanced)
-
-Connect to a remote Hindsight API server instead of running a local daemon. This is useful for:
-
- **Shared memory** across multiple OpenClaw instances
- **Production deployments** with centralized memory storage
- **Team environments** where agents share knowledge
-
-#### Plugin Configuration
-
-Configure in `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "hindsightApiUrl": "https://your-hindsight-server.com",
-          "hindsightApiToken": "your-api-token"
-        }
-      }
-    }
-  }
-}
-```
-
-**Options:**
- `hindsightApiUrl` - Full URL to external Hindsight API (e.g., `https://mcp.hindsight.example.com`)
- `hindsightApiToken` - API token for authentication (optional, only if API requires auth)
-
-#### Environment Variables (Alternative)
-
-You can also configure via environment variables:
-
-```bash
-export HINDSIGHT_EMBED_API_URL=https://your-hindsight-server.com
-export HINDSIGHT_EMBED_API_TOKEN=your-api-token  # Optional
-
-openclaw gateway
-```
-
-**Note:** Plugin config takes precedence over environment variables.
-
-#### Behavior
-
-When external API mode is enabled:
- **No local daemon** is started (no hindsight-embed process)
- **Health check** runs on startup to verify API connectivity
- **All memory operations** (retain, recall, reflect) go to the external API
- **Faster startup** since no local PostgreSQL or embedding models are needed
-
-#### Verification
-
-Check OpenClaw logs for external API mode:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# Should see on startup:
-# [Hindsight] External API mode enabled: https://your-hindsight-server.com
-# [Hindsight] External API health check passed
-```
-
-If you see daemon startup messages instead, verify your configuration is correct.
-
-## Inspecting Memories
-
-### Check Configuration
-
-View the daemon config that was written by the plugin:
-
-```bash
-cat ~/.hindsight/profiles/openclaw.env
-```
-
-This shows the LLM provider, model, port, and other settings the daemon is using.
-
-### Check Daemon Status
-
-```bash
-# Check if daemon is running
-uvx hindsight-embed@latest -p openclaw daemon status
-
-# View daemon logs
-tail -f ~/.hindsight/profiles/openclaw.log
-```
-
-### Query Memories
-
-```bash
-# Search memories
-uvx hindsight-embed@latest -p openclaw memory recall openclaw "user preferences"
-
-# View recent memories
-uvx hindsight-embed@latest -p openclaw memory list openclaw --limit 10
-
-# Open web UI (uses openclaw profile's daemon)
-uvx hindsight-embed@latest -p openclaw ui
-```
-
-## Troubleshooting
-
-### Plugin not loading
-
-```bash
-openclaw plugins list | grep hindsight
-# Should show: ✓ enabled │ Hindsight Memory │ ...
-
-# Reinstall if needed
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### Daemon not starting
-
-```bash
-# Check daemon status (note: -p openclaw uses the openclaw profile)
-uvx hindsight-embed@latest -p openclaw daemon status
-
-# View logs for errors
-tail -f ~/.hindsight/profiles/openclaw.log
-
-# Check configuration
-cat ~/.hindsight/profiles/openclaw.env
-
-# List all profiles
-uvx hindsight-embed@latest profile list
-```
-
-### No API key error
-
-Make sure you've set one of the provider API keys (or use a provider that doesn't require one):
-
-```bash
-# Option 1: OpenAI
-export OPENAI_API_KEY="sk-your-key"
-
-# Option 2: Anthropic
-export ANTHROPIC_API_KEY="your-key"
-
-# Option 3: Claude Code (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=claude-code
-
-# Option 4: OpenAI Codex (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=openai-codex
-
-# Verify it's set
-echo $OPENAI_API_KEY
-# or
-echo $HINDSIGHT_API_LLM_PROVIDER
-```
-
-### Verify it's working
-
-Check gateway logs for memory operations:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# Should see on startup:
-# [Hindsight] ✓ Using provider: openai, model: gpt-4o-mini
-# or
-# [Hindsight] ✓ Using provider: claude-code, model: claude-sonnet-4-20250514
-
-# Should see after conversations:
-# [Hindsight] Retained X messages for session ...
-# [Hindsight] Auto-recall: Injecting X memories
-```
@@ -1,188 +0,0 @@
---
-sidebar_position: 6
-title: "Pydantic AI Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Pydantic AI agents with Hindsight. Async-native retain, recall, and reflect tools — persistent memory across all agent runs with no thread-pool hacks."
---
-
-# Pydantic AI
-
-Persistent memory tools for [Pydantic AI](https://ai.pydantic.dev/) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — all async-native with no thread-pool hacks.
-
-[View Changelog →](/changelog/integrations/pydantic-ai)
-
-## Features
-
- **Async-Native Tools** — Uses Pydantic AI's async tool interface directly (`aretain`, `arecall`, `areflect`)
- **Memory Instructions** — Auto-inject relevant memories into every agent run via `instructions=[...]`
- **Three Memory Tools** — Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Simple Configuration** — Configure once globally, or pass a client directly
- **Lightweight** — Depends on `pydantic-ai-slim` to avoid pulling in all model providers
-
-## Installation
-
-```bash
-pip install hindsight-pydantic-ai
-```
-
-## Quick Start
-
-```python
-from hindsight_client import Hindsight
-from hindsight_pydantic_ai import create_hindsight_tools, memory_instructions
-from pydantic_ai import Agent
-
-client = Hindsight(base_url="http://localhost:8888")
-
-agent = Agent(
-    "openai:gpt-4o",
-    tools=create_hindsight_tools(client=client, bank_id="user-123"),
-    instructions=[memory_instructions(client=client, bank_id="user-123")],
-)
-
-result = await agent.run("What do you remember about my preferences?")
-print(result.output)
-```
-
-The agent now has three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-The `memory_instructions` callable automatically recalls relevant memories and injects them into the system prompt on every run.
-
-## Tools Only (No Auto-Injection)
-
-If you want the agent to decide when to use memory rather than always injecting context:
-
-```python
-agent = Agent(
-    "openai:gpt-4o",
-    tools=create_hindsight_tools(client=client, bank_id="user-123"),
-)
-```
-
-## Instructions Only (No Tools)
-
-If you just want memories auto-injected without giving the agent explicit memory tools:
-
-```python
-agent = Agent(
-    "openai:gpt-4o",
-    instructions=[memory_instructions(client=client, bank_id="user-123")],
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing a client to every call, configure once:
-
-```python
-from hindsight_pydantic_ai import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing client — uses global config
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Per-Tool Overrides
-
-Constructor arguments override global configuration:
-
-```python
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    budget="high",             # Override global budget
-    max_tokens=8192,           # Override global max_tokens
-    tags=["session:abc"],      # Override global tags
-)
-```
-
-## Memory Instructions Options
-
-Customize what memories get injected and how:
-
-```python
-instructions_fn = memory_instructions(
-    client=client,
-    bank_id="user-123",
-    query="relevant context about the user",  # What to search for
-    budget="low",                              # Keep it fast
-    max_results=5,                             # Limit injected memories
-    max_tokens=4096,                           # Max recall tokens
-    prefix="Relevant memories:\n",             # Text before the memory list
-    tags=["scope:global"],                     # Filter by tags
-    tags_match="any",                          # Tag match mode
-)
-```
-
-## API Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `include_retain` | `True` | Include the retain (store) tool |
-| `include_recall` | `True` | Include the recall (search) tool |
-| `include_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
@@ -1,325 +0,0 @@
---
-sidebar_position: 3
-title: "Hindsight Agent Memory Skill | AI Coding Assistant Integration"
-description: "Give AI coding assistants like Claude Code and Codex persistent memory across sessions with Hindsight's Agent Skill — a reusable prompt template for long-term context retention."
---
-
-# Skills
-
-Hindsight provides an Agent Skill that gives AI coding assistants persistent memory across sessions. Skills are reusable prompt templates that agents can load when needed to gain specialized capabilities.
-
-## Supported Platforms
-
-| Platform | Skills Directory |
-|----------|-----------------|
-| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | `~/.claude/skills/` |
-| [OpenCode](https://github.com/opencode-ai/opencode) | `~/.opencode/skills/` |
-| [Codex CLI](https://github.com/openai/codex) | `~/.codex/skills/` |
-
-## Deployment Modes
-
-The skill supports two deployment modes:
-
-| Mode | Best For | Data Location |
-|------|----------|---------------|
-| **Local** | Individual developers | Your machine (`~/.pg0/`) |
-| **Cloud** | Teams sharing knowledge | Hindsight Cloud |
-
-## Quick Install
-
-### Option 1: Interactive Installer (Recommended)
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash
-```
-
-The installer will:
-1. Prompt you to select your AI coding assistant
-2. Select deployment mode (local or cloud)
-3. Configure the appropriate settings
-4. Install the skill to the appropriate directory
-
-### Install for a Specific Platform
-
-```bash
-# Claude Code (interactive mode selection)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude
-
-# OpenCode
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app opencode
-
-# Codex CLI
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app codex
-```
-
-### Install with Cloud Mode
-
-```bash
-# Direct cloud setup (skips interactive prompts for mode)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude --mode cloud
-```
-
-### Option 2: Using add-skill
-
-If you use [add-skill](https://add-skill.org/) to manage your agent skills:
-
-```bash
-# For local mode (individual developers)
-npx add-skill vectorize-io/hindsight --skill hindsight-local
-
-# For Hindsight Cloud (teams)
-npx add-skill vectorize-io/hindsight --skill hindsight-cloud
-
-# For self-hosted Hindsight servers
-npx add-skill vectorize-io/hindsight --skill hindsight-self-hosted
-```
-
-On first use, the AI will guide you through the remaining setup:
- **Local**: Run `uvx hindsight-embed configure` to set up your LLM provider
- **Cloud**: Provide your API key and bank ID
- **Self-hosted**: Provide your server URL, API key, and bank ID
-
-## What the Skill Provides
-
-Once installed, your AI assistant gains the ability to:
-
- **Retain** - Store user preferences, learnings, and procedure outcomes
- **Recall** - Search for relevant context before starting tasks
- **Reflect** - Synthesize memories into contextual answers
-
-The skill uses the `hindsight-embed` CLI which runs a lightweight local daemon with an embedded database.
-
-## How Skills Work
-
-Skills are **model-invoked**, meaning the AI assistant automatically decides when to use them based on the context of your conversation. You don't need to explicitly trigger the skill.
-
-The assistant will:
- **Store** when you share preferences, when tasks succeed/fail, or when learnings emerge
- **Recall** before starting non-trivial tasks to get relevant context
-
-### What Gets Stored
-
-The skill is optimized to store:
-
-| Category | Examples |
-|----------|----------|
-| **User Preferences** | Coding style, tool preferences, language choices |
-| **Procedure Outcomes** | Commands that worked, configurations that resolved issues |
-| **Learnings** | Bug solutions, workarounds, architecture decisions |
-
-## Architecture
-
-### Local Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-embed CLI
-    │
-    ▼
-Local Daemon (auto-started)
-    │
-    ▼
-Embedded PostgreSQL (~/.pg0/hindsight-embed/)
-```
-
-All data stays on your machine. The daemon auto-starts when needed and shuts down after inactivity.
-
-### Cloud Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-cli
-    │
-    ▼
-Hindsight Cloud API (https://api.hindsight.vectorize.io)
-    │
-    ▼
-Shared Memory Bank (team-accessible)
-```
-
-Data is stored in Hindsight Cloud and shared across your team. All team members with the same bank ID can access shared memories.
-
---
-
-## Local Mode Setup
-
-The skill uses configuration stored in `~/.hindsight/config.env`. Reconfigure anytime:
-
-```bash
-uvx hindsight-embed configure
-```
-
---
-
-## Cloud Mode Setup
-
-Cloud mode connects to [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup), allowing teams to share memories about a codebase. When one team member learns something, everyone benefits.
-
-### Prerequisites
-
-1. A Hindsight Cloud account ([sign up](https://ui.hindsight.vectorize.io/signup))
-2. An API key from your team admin
-3. A bank ID for your project (e.g., `team-acme-frontend`)
-
-### Installation
-
-Run the installer with cloud mode:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-You'll be prompted for:
-
-| Setting | Description | Example |
-|---------|-------------|---------|
-| **Cloud API URL** | Hindsight Cloud endpoint | `https://api.hindsight.vectorize.io` |
-| **API Key** | Your authentication key | `hs_xxx...` |
-| **Bank ID** | Shared memory bank for your team | `team-acme-frontend` |
-
-### Configuration Files
-
-Cloud mode creates two files:
-
-**`~/.hindsight/config`** — API connection settings (TOML format):
-```toml
-api_url = "https://api.hindsight.vectorize.io"
-api_key = "hs_xxx..."
-```
-
-**`~/.claude/skills/hindsight/SKILL.md`** — Skill definition with your bank ID baked in.
-
-### Team Setup
-
-To set up cloud mode for your team:
-
-1. **Team admin** creates a bank in Hindsight Cloud (e.g., `team-acme-frontend`)
-2. **Team admin** generates API keys for each team member
-3. **Each developer** runs the installer with their API key and the shared bank ID
-4. All team members now share the same memory bank
-
-### What to Store in Team Banks
-
-Cloud mode uses a **shared team bank**. Be thoughtful about what goes in:
-
-| Type | Examples | How to Store |
-|------|----------|--------------|
-| **Project conventions** | Linting rules, testing requirements, Node version | `"Project uses ESLint with Airbnb config"` |
-| **Team knowledge** | Architecture decisions, common pitfalls, domain logic | `"Auth module requires Redis 7+"` |
-| **Individual preferences** | Personal coding style, communication preferences | `"Alice prefers verbose commit messages"` |
-
-**Key distinction**: Project conventions apply to everyone. Individual preferences should include the person's name so the AI knows when to apply them.
-
-### Example Workflow
-
-```
-Day 1: Alice discovers a requirement
-─────────────────────────────────────
-Alice's AI assistant stores:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-  "Alice prefers explicit error handling over silent failures"
-
-Day 2: Bob starts working on auth
-─────────────────────────────────
-Bob's AI assistant recalls:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-
-Bob avoids the same issue Alice hit!
-(Alice's personal preference is stored but won't be applied to Bob)
-```
-
-### Testing Cloud Connection
-
-After installation, verify the connection:
-
-```bash
-# Store a test memory
-hindsight memory retain team-acme-frontend "Alice works at Google as a software engineer"
-
-# Recall it
-hindsight memory recall team-acme-frontend "Alice"
-```
-
-### Switching Between Banks
-
-If you work on multiple projects, you can have different skills installed for each AI assistant, or manually switch banks:
-
-```bash
-# Environment variable override (temporary)
-HINDSIGHT_API_URL=https://api.hindsight.vectorize.io \
-HINDSIGHT_API_KEY=hs_xxx \
-hindsight memory recall different-bank "query"
-```
-
-For permanent multi-bank setups, reinstall the skill with a different bank ID.
-
-## Troubleshooting
-
-### Skill not activating
-
-The skill activates based on its description matching your request. Try being explicit:
- "Remember that..." triggers storage
- "What do you know about..." triggers recall
-
-### Local Mode Issues
-
-**Daemon not starting:**
-```bash
-uvx hindsight-embed daemon status
-uvx hindsight-embed daemon logs
-```
-
-**Reconfigure LLM provider:**
-```bash
-uvx hindsight-embed configure
-```
-
-### Cloud Mode Issues
-
-**Authentication errors:**
-```bash
-# Verify your config
-cat ~/.hindsight/config
-
-# Test connection manually
-hindsight bank list
-```
-
-**Wrong bank ID:**
-
-Check your SKILL.md file to see which bank ID is configured:
-```bash
-cat ~/.claude/skills/hindsight/SKILL.md | grep "memory retain"
-```
-
-To change the bank ID, reinstall the skill:
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-**Network/firewall issues:**
-```bash
-# Test connectivity to cloud API
-curl -I https://api.hindsight.vectorize.io/health
-```
-
-## Requirements
-
-### Local Mode
- Python 3.10+ (for `uvx`)
- An LLM API key (OpenAI, Anthropic, Groq, etc.)
-
-### Cloud Mode
- Python 3.10+ (for `uvx`)
- Hindsight Cloud API key
- Network access to `https://api.hindsight.vectorize.io`
@@ -1,157 +0,0 @@
---
-sidebar_position: 13
-title: "Strands Agents Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Strands Agents SDK agents with Hindsight. Retain, recall, and reflect tools using Strands' native @tool pattern for persistent memory across sessions."
---
-
-# Strands Agents
-
-Persistent memory tools for [Strands Agents SDK](https://github.com/strands-agents/sdk-python) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — using Strands' native `@tool` pattern.
-
-## Features
-
- **Native `@tool` Functions** - Tools are plain Python functions, compatible with `Agent(tools=[...])`
- **Memory Instructions** - Pre-recall memories for injection into agent system prompt
- **Three Memory Tools** - Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Simple Configuration** - Configure once globally, or pass a client directly
-
-## Installation
-
-```bash
-pip install hindsight-strands
-```
-
-## Quick Start
-
-```python
-from strands import Agent
-from hindsight_strands import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-agent = Agent(tools=tools)
-agent("Remember that I prefer dark mode")
-agent("What are my preferences?")
-```
-
-The agent now has three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-## With Memory Instructions
-
-Pre-recall relevant memories and inject them into the system prompt:
-
-```python
-from hindsight_strands import create_hindsight_tools, memory_instructions
-
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-memories = memory_instructions(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-agent = Agent(
-    tools=tools,
-    system_prompt=f"You are a helpful assistant.\n\n{memories}",
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-    enable_retain=True,
-    enable_recall=True,
-    enable_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing connection details to every call, configure once:
-
-```python
-from hindsight_strands import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing connection details
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Configuration Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `enable_retain` | `True` | Include the retain (store) tool |
-| `enable_recall` | `True` | Include the recall (search) tool |
-| `enable_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- strands-agents
- hindsight-client >= 0.4.0
- A running Hindsight API server
@@ -5,14 +5,70 @@
      "label": "Architecture",
      "collapsible": false,
      "items": [
-        { "type": "doc", "id": "developer/index", "label": "Overview", "customProps": { "icon": "lu-book" } },
-        { "type": "doc", "id": "developer/retain", "label": "Retain", "customProps": { "icon": "lu-brain" } },
-        { "type": "doc", "id": "developer/retrieval", "label": "Recall", "customProps": { "icon": "lu-search" } },
-        { "type": "doc", "id": "developer/reflect", "label": "Reflect", "customProps": { "icon": "lu-message" } },
-        { "type": "doc", "id": "developer/multilingual", "label": "Multilingual", "customProps": { "icon": "lu-languages" } },
-        { "type": "doc", "id": "developer/performance", "label": "Performance", "customProps": { "icon": "lu-zap" } },
-        { "type": "doc", "id": "developer/storage", "label": "Storage", "customProps": { "icon": "lu-database" } },
-        { "type": "doc", "id": "developer/rag-vs-hindsight", "label": "RAG vs Memory", "customProps": { "icon": "lu-compare" } }
+        {
+          "type": "doc",
+          "id": "developer/index",
+          "label": "Overview",
+          "customProps": {
+            "icon": "lu-book"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/retain",
+          "label": "Retain",
+          "customProps": {
+            "icon": "lu-brain"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/retrieval",
+          "label": "Recall",
+          "customProps": {
+            "icon": "lu-search"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/reflect",
+          "label": "Reflect",
+          "customProps": {
+            "icon": "lu-message"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/multilingual",
+          "label": "Multilingual",
+          "customProps": {
+            "icon": "lu-languages"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/performance",
+          "label": "Performance",
+          "customProps": {
+            "icon": "lu-zap"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/storage",
+          "label": "Storage",
+          "customProps": {
+            "icon": "lu-database"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/rag-vs-hindsight",
+          "label": "RAG vs Memory",
+          "customProps": {
+            "icon": "lu-compare"
+          }
+        }
      ]
    },
    {
@@ -20,14 +76,70 @@
      "label": "API",
      "collapsible": false,
      "items": [
-        { "type": "doc", "id": "developer/api/quickstart", "label": "Quick Start", "customProps": { "icon": "lu-rocket" } },
-        { "type": "doc", "id": "developer/api/retain", "label": "Retain", "customProps": { "icon": "lu-brain" } },
-        { "type": "doc", "id": "developer/api/recall", "label": "Recall", "customProps": { "icon": "lu-search" } },
-        { "type": "doc", "id": "developer/api/reflect", "label": "Reflect", "customProps": { "icon": "lu-message" } },
-        { "type": "doc", "id": "developer/api/memory-banks", "label": "Memory Banks", "customProps": { "icon": "lu-memory" } },
-        { "type": "doc", "id": "developer/api/entities", "label": "Entities", "customProps": { "icon": "lu-network" } },
-        { "type": "doc", "id": "developer/api/documents", "label": "Documents", "customProps": { "icon": "lu-file" } },
-        { "type": "doc", "id": "developer/api/operations", "label": "Operations", "customProps": { "icon": "lu-cpu" } }
+        {
+          "type": "doc",
+          "id": "developer/api/quickstart",
+          "label": "Quick Start",
+          "customProps": {
+            "icon": "lu-rocket"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/retain",
+          "label": "Retain",
+          "customProps": {
+            "icon": "lu-brain"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/recall",
+          "label": "Recall",
+          "customProps": {
+            "icon": "lu-search"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/reflect",
+          "label": "Reflect",
+          "customProps": {
+            "icon": "lu-message"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/memory-banks",
+          "label": "Memory Banks",
+          "customProps": {
+            "icon": "lu-memory"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/entities",
+          "label": "Entities",
+          "customProps": {
+            "icon": "lu-network"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/documents",
+          "label": "Documents",
+          "customProps": {
+            "icon": "lu-file"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/api/operations",
+          "label": "Operations",
+          "customProps": {
+            "icon": "lu-cpu"
+          }
+        }
      ]
    },
    {
@@ -35,9 +147,30 @@
      "label": "Clients",
      "collapsible": false,
      "items": [
-        { "type": "doc", "id": "sdks/python", "label": "Python", "customProps": { "icon": "si-python" } },
-        { "type": "doc", "id": "sdks/nodejs", "label": "TypeScript", "customProps": { "icon": "/img/icons/typescript.png" } },
-        { "type": "doc", "id": "sdks/cli", "label": "CLI", "customProps": { "icon": "lu-terminal" } }
+        {
+          "type": "doc",
+          "id": "sdks/python",
+          "label": "Python",
+          "customProps": {
+            "icon": "si-python"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "sdks/nodejs",
+          "label": "TypeScript",
+          "customProps": {
+            "icon": "/img/icons/typescript.png"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "sdks/cli",
+          "label": "CLI",
+          "customProps": {
+            "icon": "lu-terminal"
+          }
+        }
      ]
    },
    {
@@ -45,9 +178,30 @@
      "label": "Integrations",
      "collapsible": false,
      "items": [
-        { "type": "doc", "id": "sdks/integrations/local-mcp", "label": "Local MCP Server", "customProps": { "icon": "/img/icons/mcp.png" } },
-        { "type": "doc", "id": "sdks/integrations/litellm", "label": "LiteLLM", "customProps": { "icon": "/img/icons/litellm.png" } },
-        { "type": "doc", "id": "sdks/integrations/skills", "label": "Skills", "customProps": { "icon": "/img/icons/skills.png" } }
+        {
+          "type": "link",
+          "label": "Local MCP Server",
+          "customProps": {
+            "icon": "/img/icons/mcp.png"
+          },
+          "href": "/sdks/integrations/local-mcp"
+        },
+        {
+          "type": "link",
+          "label": "LiteLLM",
+          "customProps": {
+            "icon": "/img/icons/litellm.png"
+          },
+          "href": "/sdks/integrations/litellm"
+        },
+        {
+          "type": "link",
+          "label": "Skills",
+          "customProps": {
+            "icon": "/img/icons/skills.png"
+          },
+          "href": "/sdks/integrations/skills"
+        }
      ]
    },
    {
@@ -55,14 +209,70 @@
      "label": "Hosting",
      "collapsible": false,
      "items": [
-        { "type": "doc", "id": "developer/installation", "label": "Installation", "customProps": { "icon": "lu-package" } },
-        { "type": "doc", "id": "developer/services", "label": "Services", "customProps": { "icon": "lu-server" } },
-        { "type": "doc", "id": "developer/configuration", "label": "Configuration", "customProps": { "icon": "lu-settings" } },
-        { "type": "doc", "id": "developer/admin-cli", "label": "Admin CLI", "customProps": { "icon": "lu-terminal" } },
-        { "type": "doc", "id": "developer/extensions", "label": "Extensions", "customProps": { "icon": "lu-plug" } },
-        { "type": "doc", "id": "developer/models", "label": "Models", "customProps": { "icon": "lu-cpu" } },
-        { "type": "doc", "id": "developer/monitoring", "label": "Monitoring", "customProps": { "icon": "lu-activity" } },
-        { "type": "doc", "id": "developer/mcp-server", "label": "MCP Server", "customProps": { "icon": "lu-network" } }
+        {
+          "type": "doc",
+          "id": "developer/installation",
+          "label": "Installation",
+          "customProps": {
+            "icon": "lu-package"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/services",
+          "label": "Services",
+          "customProps": {
+            "icon": "lu-server"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/configuration",
+          "label": "Configuration",
+          "customProps": {
+            "icon": "lu-settings"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/admin-cli",
+          "label": "Admin CLI",
+          "customProps": {
+            "icon": "lu-terminal"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/extensions",
+          "label": "Extensions",
+          "customProps": {
+            "icon": "lu-plug"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/models",
+          "label": "Models",
+          "customProps": {
+            "icon": "lu-cpu"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/monitoring",
+          "label": "Monitoring",
+          "customProps": {
+            "icon": "lu-activity"
+          }
+        },
+        {
+          "type": "doc",
+          "id": "developer/mcp-server",
+          "label": "MCP Server",
+          "customProps": {
+            "icon": "lu-network"
+          }
+        }
      ]
    }
  ]
@@ -220,140 +220,140 @@
      "collapsible": false,
      "items": [
        {
-          "type": "doc",
-          "id": "sdks/integrations/local-mcp",
+          "type": "link",
          "label": "Local MCP Server",
          "customProps": {
            "icon": "/img/icons/mcp.png"
-          }
+          },
+          "href": "/sdks/integrations/local-mcp"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/litellm",
+          "type": "link",
          "label": "LiteLLM",
          "customProps": {
            "icon": "/img/icons/litellm.png"
-          }
+          },
+          "href": "/sdks/integrations/litellm"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/claude-code",
+          "type": "link",
          "label": "Claude Code",
          "customProps": {
            "icon": "/img/icons/claudecode.svg"
-          }
+          },
+          "href": "/sdks/integrations/claude-code"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/codex",
+          "type": "link",
          "label": "OpenAI Codex CLI",
          "customProps": {
            "icon": "/img/icons/terminal.svg"
-          }
+          },
+          "href": "/sdks/integrations/codex"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/openclaw",
+          "type": "link",
          "label": "OpenClaw",
          "customProps": {
            "icon": "/img/icons/openclaw.png"
-          }
+          },
+          "href": "/sdks/integrations/openclaw"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/ai-sdk",
+          "type": "link",
          "label": "Vercel AI SDK",
          "customProps": {
            "icon": "/img/icons/vercel.png"
-          }
+          },
+          "href": "/sdks/integrations/ai-sdk"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/chat",
+          "type": "link",
          "label": "Vercel Chat SDK",
          "customProps": {
            "icon": "/img/icons/vercel.png"
-          }
+          },
+          "href": "/sdks/integrations/chat"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/crewai",
+          "type": "link",
          "label": "CrewAI",
          "customProps": {
            "icon": "/img/icons/crewai.png"
-          }
+          },
+          "href": "/sdks/integrations/crewai"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/pydantic-ai",
+          "type": "link",
          "label": "Pydantic AI",
          "customProps": {
            "icon": "/img/icons/pydanticai.png"
-          }
+          },
+          "href": "/sdks/integrations/pydantic-ai"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/agno",
+          "type": "link",
          "label": "Agno",
          "customProps": {
            "icon": "/img/icons/agno.png"
-          }
+          },
+          "href": "/sdks/integrations/agno"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/hermes",
+          "type": "link",
          "label": "Hermes Agent",
          "customProps": {
            "icon": "/img/icons/hermes.png"
-          }
+          },
+          "href": "/sdks/integrations/hermes"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/langgraph",
+          "type": "link",
          "label": "LangGraph / LangChain",
          "customProps": {
            "icon": "/img/icons/langgraph.png"
-          }
+          },
+          "href": "/sdks/integrations/langgraph"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/nemoclaw",
+          "type": "link",
          "label": "NemoClaw",
          "customProps": {
            "icon": "/img/icons/nemoclaw.png"
-          }
+          },
+          "href": "/sdks/integrations/nemoclaw"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/strands",
+          "type": "link",
          "label": "Strands Agents",
          "customProps": {
            "icon": "/img/icons/strands.png"
-          }
+          },
+          "href": "/sdks/integrations/strands"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/ag2",
+          "type": "link",
          "label": "AG2",
          "customProps": {
            "icon": "/img/icons/ag2.svg"
-          }
+          },
+          "href": "/sdks/integrations/ag2"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/llamaindex",
+          "type": "link",
          "label": "LlamaIndex",
          "customProps": {
            "icon": "/img/icons/llamaindex.png"
-          }
+          },
+          "href": "/sdks/integrations/llamaindex"
        },
        {
-          "type": "doc",
-          "id": "sdks/integrations/skills",
+          "type": "link",
          "label": "Skills",
          "customProps": {
            "icon": "/img/icons/skills.png"
-          }
+          },
+          "href": "/sdks/integrations/skills"
        }
      ]
    },
@@ -42,6 +42,9 @@ fi
 echo "======================================"
 echo ""

+# Number of retry attempts for each example (handles transient LLM timeouts)
+MAX_RETRIES=2
+
 # Function to run a single example
 run_example() {
    local file="$1"
@@ -54,19 +57,30 @@ run_example() {
    echo -n "Running $basename... "

    pushd "$workdir" > /dev/null 2>&1
-    if $runner "$file" > "$logfile" 2>&1; then
-        echo -e "${GREEN}✓ PASS${NC}"
-        TOTAL_PASSED=$((TOTAL_PASSED + 1))
-        rm -f "$logfile"  # Clean up successful test logs
-        popd > /dev/null 2>&1
-        return 0
-    else
-        echo -e "${RED}✗ FAIL${NC}"
-        TOTAL_FAILED=$((TOTAL_FAILED + 1))
-        FAILED_EXAMPLES+=("$basename:$logfile")
-        popd > /dev/null 2>&1
-        return 1
-    fi
+    local attempt=1
+    while [ $attempt -le $MAX_RETRIES ]; do
+        if $runner "$file" > "$logfile" 2>&1; then
+            if [ $attempt -gt 1 ]; then
+                echo -e "${GREEN}✓ PASS${NC} (passed on retry $attempt)"
+            else
+                echo -e "${GREEN}✓ PASS${NC}"
+            fi
+            TOTAL_PASSED=$((TOTAL_PASSED + 1))
+            rm -f "$logfile"  # Clean up successful test logs
+            popd > /dev/null 2>&1
+            return 0
+        fi
+        if [ $attempt -lt $MAX_RETRIES ]; then
+            echo -e -n "${YELLOW}(attempt $attempt failed, retrying)${NC} "
+        fi
+        attempt=$((attempt + 1))
+    done
+
+    echo -e "${RED}✗ FAIL${NC} (after $MAX_RETRIES attempts)"
+    TOTAL_FAILED=$((TOTAL_FAILED + 1))
+    FAILED_EXAMPLES+=("$basename:$logfile")
+    popd > /dev/null 2>&1
+    return 1
 }

 # Run Python examples
@@ -6,4 +6,4 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="Vercel AI SDK Changelog" subtitle="@vectorize-io/hindsight-ai-sdk — memory integration for Vercel AI SDK." />

-[← Vercel AI SDK integration](../../sdks/integrations/ai-sdk.md)
+← Vercel AI SDK integration
@@ -6,4 +6,4 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="Vercel Chat SDK Changelog" subtitle="@vectorize-io/hindsight-chat — memory integration for Vercel Chat SDK." />

-[← Vercel Chat SDK integration](../../sdks/integrations/chat.md)
+← Vercel Chat SDK integration
@@ -6,7 +6,7 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="Claude Code Changelog" subtitle="hindsight-memory — Hindsight memory plugin for Claude Code." />

-[← Claude Code integration](../../sdks/integrations/claude-code.md)
+← Claude Code integration

 ## [0.3.0](https://github.com/vectorize-io/hindsight/tree/integrations/claude-code/v0.3.0)

@@ -6,4 +6,4 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="CrewAI Changelog" subtitle="hindsight-crewai — persistent memory for CrewAI agents." />

-[← CrewAI integration](../../sdks/integrations/crewai.md)
+← CrewAI integration
@@ -6,7 +6,7 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="LangGraph Changelog" subtitle="hindsight-langgraph — LangGraph and LangChain memory integration." />

-[← LangGraph integration](../../sdks/integrations/langgraph.md)
+← LangGraph integration

 ## [0.1.1](https://github.com/vectorize-io/hindsight/tree/integrations/langgraph/v0.1.1)

@@ -6,7 +6,7 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="LiteLLM Changelog" subtitle="hindsight-litellm — universal LLM memory integration via LiteLLM." />

-[← LiteLLM integration](../../sdks/integrations/litellm.md)
+← LiteLLM integration

 ## [0.5.0](https://github.com/vectorize-io/hindsight/tree/integrations/litellm/v0.5.0)

@@ -6,7 +6,7 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="NemoClaw Changelog" subtitle="@vectorize-io/hindsight-nemoclaw — persistent memory for NemoClaw sandboxed agents." />

-[← NemoClaw integration](../../sdks/integrations/nemoclaw.md)
+← NemoClaw integration

 ## [0.1.1](https://github.com/vectorize-io/hindsight/tree/integrations/nemoclaw/v0.1.1)

@@ -6,7 +6,7 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="OpenClaw Changelog" subtitle="@vectorize-io/hindsight-openclaw — Hindsight memory plugin for OpenClaw." />

-[← OpenClaw integration](../../sdks/integrations/openclaw.md)
+← OpenClaw integration

 ## [0.5.1](https://github.com/vectorize-io/hindsight/tree/integrations/openclaw/v0.5.1)

@@ -6,4 +6,4 @@ import PageHero from '@site/src/components/PageHero';

 <PageHero title="Pydantic AI Changelog" subtitle="hindsight-pydantic-ai — persistent memory tools for Pydantic AI agents." />

-[← Pydantic AI integration](../../sdks/integrations/pydantic-ai.md)
+← Pydantic AI integration
@@ -277,7 +277,7 @@ console.log('Would apply config:', dryRunResult.config_applied);
 ```bash
 curl -X POST "$HINDSIGHT_URL/v1/default/banks/my-bank/import?dry_run=true" \
  -H "Content-Type: application/json" \
-  -d @template.json
+  -d '{"version": "1", "bank": {"retain_mission": "Dry run test."}}'
 ```

 ### Go
@@ -293,19 +293,50 @@ console.log(`Last refreshed: ${mentalModel.last_refreshed_at}`);
 # Section 'get-mental-model' not found in api/mental-models.go
 ```

+### Detail Levels
+
+Both **List** and **Get** endpoints accept an optional `detail` query parameter that controls how much data is returned. This is useful for reducing response size, especially in agent boot flows or MCP clients where context budget is limited.
+
+| Level | Fields Returned | Use Case |
+|-------|----------------|----------|
+| `metadata` | `id`, `bank_id`, `name`, `tags`, `last_refreshed_at`, `created_at` | Inventory — "what models exist?" |
+| `content` | All metadata fields + `source_query`, `content`, `max_tokens`, `trigger` | Agent boot — "what do the models say?" |
+| `full` (default) | All fields including `reflect_response` | Deep inspection — "what evidence backs this model?" |
+
+```bash
+# List only names and tags (smallest response)
+curl "$BASE_URL/v1/default/banks/$BANK_ID/mental-models?detail=metadata"
+
+# List with content but without provenance chains
+curl "$BASE_URL/v1/default/banks/$BANK_ID/mental-models?detail=content"
+
+# Get full detail (default behavior)
+curl "$BASE_URL/v1/default/banks/$BANK_ID/mental-models/$MODEL_ID?detail=full"
+```
+
+The `detail` parameter is also available in the MCP tools:
+
+```json
+{"bank_id": "my-bank", "detail": "metadata"}
+```
+
+:::tip
+Use `detail=content` for agent orientation flows. It includes everything the agent needs to understand the models without the heavyweight `reflect_response` provenance chains, which can exceed 200KB for banks with many models.
 ### Response Fields

-| Field | Type | Description |
-|-------|------|-------------|
-| `id` | string | Unique mental model ID |
-| `bank_id` | string | Memory bank ID |
-| `name` | string | Human-readable name |
-| `source_query` | string | The query used to generate content |
-| `content` | string | The generated mental model text |
-| `tags` | list | Tags for filtering |
-| `last_refreshed_at` | string | When the mental model was last updated |
-| `created_at` | string | When the mental model was created |
-| `reflect_response` | object | Full reflect response including `based_on` facts |
+| Field | Type | Detail Level | Description |
+|-------|------|-------------|-------------|
+| `id` | string | metadata | Unique mental model ID |
+| `bank_id` | string | metadata | Memory bank ID |
+| `name` | string | metadata | Human-readable name |
+| `tags` | list | metadata | Tags for filtering |
+| `last_refreshed_at` | string | metadata | When the mental model was last updated |
+| `created_at` | string | metadata | When the mental model was created |
+| `source_query` | string | content | The query used to generate content |
+| `content` | string | content | The generated mental model text |
+| `max_tokens` | int | content | Maximum tokens for the mental model content |
+| `trigger` | object | content | Trigger settings (see [Automatic Refresh](#automatic-refresh)) |
+| `reflect_response` | object | full | Full reflect response including `based_on` provenance facts |

 ---

@@ -971,6 +971,23 @@
            },
            "description": "How to match tags"
          },
+          {
+            "name": "detail",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "enum": [
+                "metadata",
+                "content",
+                "full"
+              ],
+              "type": "string",
+              "description": "Detail level: 'metadata' (names/tags only), 'content' (adds content/config), 'full' (includes reflect_response)",
+              "default": "full",
+              "title": "Detail"
+            },
+            "description": "Detail level: 'metadata' (names/tags only), 'content' (adds content/config), 'full' (includes reflect_response)"
+          },
          {
            "name": "limit",
            "in": "query",
@@ -1129,6 +1146,23 @@
              "title": "Mental Model Id"
            }
          },
+          {
+            "name": "detail",
+            "in": "query",
+            "required": false,
+            "schema": {
+              "enum": [
+                "metadata",
+                "content",
+                "full"
+              ],
+              "type": "string",
+              "description": "Detail level: 'metadata' (names/tags only), 'content' (adds content/config), 'full' (includes reflect_response)",
+              "default": "full",
+              "title": "Detail"
+            },
+            "description": "Detail level: 'metadata' (names/tags only), 'content' (adds content/config), 'full' (includes reflect_response)"
+          },
          {
            "name": "authorization",
            "in": "header",
@@ -7261,11 +7295,25 @@
            "title": "Name"
          },
          "source_query": {
-            "type": "string",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
            "title": "Source Query"
          },
          "content": {
-            "type": "string",
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
            "title": "Content",
            "description": "The mental model content as well-formatted markdown (auto-generated from reflect endpoint)"
          },
@@ -7278,13 +7326,25 @@
            "default": []
          },
          "max_tokens": {
-            "type": "integer",
-            "title": "Max Tokens",
-            "default": 2048
+            "anyOf": [
+              {
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "title": "Max Tokens"
          },
          "trigger": {
-            "$ref": "#/components/schemas/MentalModelTrigger-Output",
-            "default": {}
+            "anyOf": [
+              {
+                "$ref": "#/components/schemas/MentalModelTrigger-Output"
+              },
+              {
+                "type": "null"
+              }
+            ]
          },
          "last_refreshed_at": {
            "anyOf": [
@@ -7326,9 +7386,7 @@
        "required": [
          "id",
          "bank_id",
-          "name",
-          "source_query",
-          "content"
+          "name"
        ],
        "title": "MentalModelResponse",
        "description": "Response model for a mental model (stored reflect response)."
@@ -1,184 +0,0 @@
---
-sidebar_position: 8
-title: "AG2 (AutoGen) Persistent Memory with Hindsight | Integration Guide"
-description: "Add long-term persistent memory to your AG2 (AutoGen) agents with Hindsight. Automatic fact extraction, entity tracking, and recall tools that persist across conversations."
---
-
-# AG2
-
-Persistent long-term memory for [AG2](https://ag2.ai) agents (community AutoGen fork). Give your agents retain/recall/reflect tools that persist across conversations.
-
-[View Changelog →](../../changelog/integrations/ag2.md)
-
-## Features
-
- **Drop-in Tools** — `register_hindsight_tools()` registers retain, recall, and reflect in one line
- **AG2-native** — Uses `Annotated` type hints compatible with AG2's `@register_for_llm` / `@register_for_execution` pattern
- **GroupChat Support** — Multiple agents can share a single memory bank
- **Selective Tools** — Include only the tools you need (`include_retain`, `include_recall`, `include_reflect`)
- **Simple Configuration** — Configure once globally or override per tool set
-
-## Installation
-
-```bash
-pip install hindsight-ag2
-```
-
-## Quick Start
-
-```python
-from autogen import AssistantAgent, UserProxyAgent, LLMConfig
-from hindsight_ag2 import register_hindsight_tools
-
-llm_config = LLMConfig(api_type="openai", model="gpt-4o-mini")
-
-with llm_config:
-    assistant = AssistantAgent(
-        name="assistant",
-        system_message="You are a helpful assistant with long-term memory.",
-    )
-    user_proxy = UserProxyAgent(
-        name="user",
-        human_input_mode="NEVER",
-    )
-
-# Register Hindsight memory tools on both agents
-register_hindsight_tools(
-    assistant, user_proxy,
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-)
-
-# The assistant can now use hindsight_retain, hindsight_recall, hindsight_reflect
-result = user_proxy.initiate_chat(
-    assistant,
-    message="Remember that I prefer Python over JavaScript.",
-)
-```
-
-That's it. The assistant can now store and retrieve memories across conversations.
-
-## How It Works
-
-The integration provides three AG2-compatible tool functions backed by Hindsight's API:
-
-| Tool | Hindsight | What happens |
-|------|-----------|--------------|
-| `hindsight_retain(content)` | `retain(bank_id, content, ...)` | Content is stored. Hindsight extracts facts, entities, and relationships from the raw text. |
-| `hindsight_recall(query)` | `recall(bank_id, query, ...)` | Hindsight runs semantic search, BM25, graph traversal, and reranking. Returns a numbered list of matching memories. |
-| `hindsight_reflect(query)` | `reflect(bank_id, query, ...)` | Hindsight synthesizes a reasoned answer from all relevant memories, using the bank's disposition traits. |
-
-Tools are plain Python functions with `Annotated` type hints. AG2 uses these hints to generate the tool schema that the LLM sees.
-
-## Configuration
-
-### Global Configuration
-
-```python
-from hindsight_ag2 import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-key",       # or set HINDSIGHT_API_KEY env var
-    budget="mid",              # low / mid / high
-    max_tokens=4096,
-    tags=["source:ag2"],       # default tags for retain
-)
-```
-
-### Per-Tool Overrides
-
-Constructor arguments override global configuration:
-
-```python
-from hindsight_ag2 import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-    budget="high",
-    max_tokens=8192,
-    tags=["team:alpha"],
-)
-```
-
-## GroupChat with Shared Memory
-
-Multiple agents can share a single memory bank in a GroupChat:
-
-```python
-from autogen import AssistantAgent, UserProxyAgent, GroupChat, GroupChatManager, LLMConfig
-from hindsight_ag2 import register_hindsight_tools
-
-llm_config = LLMConfig(api_type="openai", model="gpt-4o-mini")
-
-with llm_config:
-    researcher = AssistantAgent(name="researcher", system_message="You research topics.")
-    writer = AssistantAgent(name="writer", system_message="You write content.")
-    executor = UserProxyAgent(name="executor", human_input_mode="NEVER")
-
-# All agents share the same memory bank
-for agent in [researcher, writer]:
-    register_hindsight_tools(agent, executor, bank_id="team-memory")
-
-group_chat = GroupChat(agents=[researcher, writer, executor], messages=[])
-manager = GroupChatManager(groupchat=group_chat)
-```
-
-## Manual Registration
-
-For full control over how tools are registered:
-
-```python
-from hindsight_ag2 import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="my-bank",
-    hindsight_api_url="http://localhost:8888",
-)
-for tool_fn in tools:
-    assistant.register_for_llm(description=tool_fn.__doc__)(tool_fn)
-    user_proxy.register_for_execution()(tool_fn)
-```
-
-## API Reference
-
-### Configuration
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Set global connection and default settings |
-| `get_config()` | Get current configuration |
-| `reset_config()` | Reset configuration to None |
-
-### create_hindsight_tools
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured `Hindsight` client |
-| `hindsight_api_url` | from config | Hindsight API URL |
-| `api_key` | from config | API key |
-| `budget` | `"mid"` | Recall/reflect budget (low/mid/high) |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode (any/all/any_strict/all_strict) |
-| `retain_metadata` | `None` | Metadata dict for retain operations |
-| `retain_document_id` | `None` | Document ID for retain (groups/upserts memories) |
-| `recall_types` | `None` | Fact types to filter (world, experience, opinion, observation) |
-| `recall_include_entities` | `False` | Include entity information in recall results |
-| `reflect_context` | `None` | Additional context for reflect operations |
-| `reflect_max_tokens` | `max_tokens` | Max tokens for reflect results |
-| `reflect_response_schema` | `None` | JSON schema to constrain reflect output format |
-| `reflect_tags` | `recall_tags` | Tags to filter memories used in reflect |
-| `reflect_tags_match` | `recall_tags_match` | Tag matching for reflect |
-| `include_retain` | `True` | Include the retain tool |
-| `include_recall` | `True` | Include the recall tool |
-| `include_reflect` | `True` | Include the reflect tool |
-
-## Requirements
-
- Python >= 3.10
- ag2 >= 0.9.0
- A running Hindsight API server
@@ -1,188 +0,0 @@
---
-sidebar_position: 9
-title: "Agno Agent Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to Agno agents using Hindsight's retain, recall, and reflect tools. Plug into Agno's native Toolkit pattern for long-term memory across sessions."
---
-
-# Agno
-
-Persistent memory tools for [Agno](https://github.com/agno-agi/agno) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — using Agno's native Toolkit pattern.
-
-## Features
-
- **Native Toolkit** - Extends Agno's `Toolkit` base class, just like `Mem0Tools`
- **Memory Instructions** - Pre-recall memories for injection into `Agent(instructions=[...])`
- **Three Memory Tools** - Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Flexible Bank Resolution** - Static bank ID, `RunContext.user_id`, or custom resolver
- **Simple Configuration** - Configure once globally, or pass a client directly
-
-## Installation
-
-```bash
-pip install hindsight-agno
-```
-
-## Quick Start
-
-```python
-from agno.agent import Agent
-from agno.models.openai import OpenAIChat
-from hindsight_agno import HindsightTools
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-
-agent.print_response("Remember that I prefer dark mode")
-agent.print_response("What are my preferences?")
-```
-
-The agent now has three tools it can call:
-
- **`retain_memory`** — Store information to long-term memory
- **`recall_memory`** — Search long-term memory for relevant facts
- **`reflect_on_memory`** — Synthesize a reasoned answer from memories
-
-## With Memory Instructions
-
-Pre-recall relevant memories and inject them into the system prompt:
-
-```python
-from hindsight_agno import HindsightTools, memory_instructions
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-    instructions=[memory_instructions(
-        bank_id="user-123",
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = [HindsightTools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-    enable_retain=True,
-    enable_recall=True,
-    enable_reflect=False,  # Omit reflect
-)]
-```
-
-## Bank Resolution
-
-The bank ID is resolved in order:
-
-1. **`bank_resolver`** — Custom callable `(RunContext) -> str`
-2. **`bank_id`** — Static bank ID passed to constructor
-3. **`run_context.user_id`** — Automatic per-user banks
-
-```python
-# Per-user banks from RunContext
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(hindsight_api_url="http://localhost:8888")],
-    user_id="user-123",  # Used as bank_id
-)
-
-# Custom resolver
-def resolve_bank(ctx):
-    return f"team-{ctx.user_id}"
-
-agent = Agent(
-    model=OpenAIChat(id="gpt-4o-mini"),
-    tools=[HindsightTools(
-        bank_resolver=resolve_bank,
-        hindsight_api_url="http://localhost:8888",
-    )],
-)
-```
-
-## Global Configuration
-
-Instead of passing connection details to every toolkit, configure once:
-
-```python
-from hindsight_agno import configure, HindsightTools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create toolkit without passing connection details
-tools = [HindsightTools(bank_id="user-123")]
-```
-
-## Configuration Reference
-
-### `HindsightTools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static Hindsight memory bank ID |
-| `bank_resolver` | `None` | Callable `(RunContext) -> str` for dynamic bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `enable_retain` | `True` | Include the retain (store) tool |
-| `enable_recall` | `True` | Include the recall (search) tool |
-| `enable_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- agno
- hindsight-client >= 0.4.0
- A running Hindsight API server
@@ -1,196 +0,0 @@
-
-# Vercel AI SDK
-
-The `@vectorize-io/hindsight-ai-sdk` package integrates [Hindsight](https://hindsight.vectorize.io) memory with the [Vercel AI SDK](https://ai-sdk.dev). It provides five ready-to-use tools for retaining, recalling, and reflecting on long-term memories.
-
-[View Changelog →](../../changelog/integrations/ai-sdk.md)
-
-## Installation
-
-```bash
-npm install @vectorize-io/hindsight-ai-sdk @vectorize-io/hindsight-client ai
-```
-
-## Setup
-
-Create a Hindsight client and pass it to `createHindsightTools` along with a `bankId`. The `bankId` identifies the memory store for this session—typically a user ID.
-
-```typescript
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-import { createHindsightTools } from '@vectorize-io/hindsight-ai-sdk';
-
-const client = new HindsightClient({ baseUrl: 'http://localhost:8888' });
-
-const tools = createHindsightTools({
-  client,
-  bankId: 'user-123',
-});
-```
-
-> **💡 Per-request bank IDs**
-> 
-In multi-user applications, create `tools` inside your request handler so each request closes over the correct `bankId`. See the [Next.js example](#in-a-nextjs-route-handler) below.
-## Usage
-
-### With `generateText`
-
-```typescript
-import { generateText } from 'ai';
-import { openai } from '@ai-sdk/openai';
-
-const { text } = await generateText({
-  model: openai('gpt-4o'),
-  tools,
-  maxSteps: 5,
-  system: 'You are a helpful assistant with long-term memory.',
-  prompt: 'Remember that I prefer dark mode and large fonts.',
-});
-```
-
-### With `streamText`
-
-```typescript
-import { streamText } from 'ai';
-
-const result = streamText({
-  model: openai('gpt-4o'),
-  tools,
-  maxSteps: 5,
-  system: 'You are a helpful assistant with long-term memory.',
-  prompt: 'What are my display preferences?',
-});
-
-for await (const chunk of result.textStream) {
-  process.stdout.write(chunk);
-}
-```
-
-### With `ToolLoopAgent`
-
-```typescript
-import { generateText, ToolLoopAgent, stepCountIs } from 'ai';
-import { openai } from '@ai-sdk/openai';
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-import { createHindsightTools } from '@vectorize-io/hindsight-ai-sdk';
-
-const client = new HindsightClient({ baseUrl: process.env.HINDSIGHT_API_URL! });
-
-const agent = new ToolLoopAgent({
-  model: openai('gpt-4o'),
-  tools: createHindsightTools({ client, bankId: 'user-123' }),
-  stopWhen: stepCountIs(10),
-  system: 'You are a helpful assistant with long-term memory.',
-});
-
-const result = await agent.generate({
-  prompt: 'Remember that my favorite editor is Neovim',
-});
-```
-
-### In a Next.js Route Handler
-
-```typescript
-// app/api/chat/route.ts
-import { streamText } from 'ai';
-import { openai } from '@ai-sdk/openai';
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-import { createHindsightTools } from '@vectorize-io/hindsight-ai-sdk';
-
-const hindsightClient = new HindsightClient({
-  baseUrl: process.env.HINDSIGHT_API_URL!,
-});
-
-export async function POST(req: Request) {
-  const { messages, userId } = await req.json();
-
-  // Tools are created per-request, closing over the current user's bankId
-  const tools = createHindsightTools({
-    client: hindsightClient,
-    bankId: userId,
-  });
-
-  return streamText({
-    model: openai('gpt-4o'),
-    tools,
-    maxSteps: 5,
-    system: 'You are a helpful assistant with long-term memory.',
-    messages,
-  }).toDataStreamResponse();
-}
-```
-
---
-
-## Tools Reference
-
-Five tools are registered. The `bankId` is fixed at creation time—the agent cannot change it.
-
-| Tool | What the agent provides | What the constructor controls |
-|------|------------------------|-------------------------------|
-| `retain` | `content`, `documentId`, `timestamp`, `context` | `async`, `tags`, `metadata` |
-| `recall` | `query`, `queryTimestamp` | `budget`, `types`, `maxTokens`, `includeEntities`, `includeChunks` |
-| `reflect` | `query`, `context` | `budget` |
-| `getMentalModel` | `mentalModelId` | — |
-| `getDocument` | `documentId` | — |
-
-**Why this split?** Semantic inputs (what to remember, what to search for) belong to the agent. Infrastructure concerns (cost budget, tagging strategy, async mode) belong to the application.
-
---
-
-## Constructor Options
-
-All options except `client` and `bankId` are optional. Each tool's options are grouped under the tool name.
-
-```typescript
-const tools = createHindsightTools({
-  client,
-  bankId: userId,
-
-  retain: {
-    async: true,                        // fire-and-forget (default: false)
-    tags: ['env:prod', 'app:support'],  // always attached to every retained memory
-    metadata: { version: '2.0' },       // always attached to every retained memory
-  },
-
-  recall: {
-    budget: 'high',                     // processing depth: low | mid | high (default: 'mid')
-    types: ['experience', 'world'],     // restrict to these fact types (default: all)
-    maxTokens: 2048,                    // cap token budget (default: API default)
-    includeEntities: true,              // include entity observations (default: false)
-    includeChunks: true,                // include raw source chunks (default: false)
-  },
-
-  reflect: {
-    budget: 'mid',                      // processing depth (default: 'mid')
-  },
-
-});
-```
-
-### `retain`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `async` | `boolean` | `false` | Fire-and-forget — do not wait for ingestion to complete |
-| `tags` | `string[]` | — | Tags attached to every retained memory |
-| `metadata` | `Record<string, string>` | — | Metadata attached to every retained memory |
-| `description` | `string` | built-in | Override the tool description shown to the model |
-
-### `recall`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Controls retrieval depth and latency |
-| `types` | `('world' \| 'experience' \| 'observation')[]` | all | Restrict results to these fact types |
-| `maxTokens` | `number` | API default | Cap the total tokens returned |
-| `includeEntities` | `boolean` | `false` | Include entity observations in results |
-| `includeChunks` | `boolean` | `false` | Include raw source chunks in results |
-| `description` | `string` | built-in | Override the tool description shown to the model |
-
-### `reflect`
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Controls synthesis depth and latency |
-| `maxTokens` | `number` | API default | Maximum tokens for the response |
-| `description` | `string` | built-in | Override the tool description shown to the model |
@@ -1,222 +0,0 @@
---
-sidebar_position: 12
---
-
-# AutoGen
-
-Persistent long-term memory for [AutoGen](https://microsoft.github.io/autogen/) agents via Hindsight. Provides `FunctionTool` instances that plug directly into AutoGen's `AssistantAgent`.
-
-## Features
-
- **Memory Tools** — retain, recall, and reflect as AutoGen `FunctionTool` instances compatible with `AssistantAgent(tools=[...])`
- **Async-Native** — Uses `aretain`, `arecall`, `areflect` directly — works seamlessly in AutoGen's async runtime
- **Selective Tools** — Include only the tools you need with `include_retain/recall/reflect` flags
- **Tag-Based Scoping** — Partition memories by topic, session, or user with tags
- **Global Configuration** — Configure once with `configure()`, create tools anywhere
-
-## Installation
-
-```bash
-pip install hindsight-autogen autogen-agentchat "autogen-ext[openai]"
-```
-
-`hindsight-autogen` pulls in `autogen-core` and `hindsight-client`. You also need `autogen-agentchat` for `AssistantAgent` and `autogen-ext[openai]` for the OpenAI model client.
-
-## Quick Start
-
-```python
-import asyncio
-from autogen_agentchat.agents import AssistantAgent
-from autogen_ext.models.openai import OpenAIChatCompletionClient
-from hindsight_client import Hindsight
-from hindsight_autogen import create_hindsight_tools
-
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-    await client.acreate_bank(bank_id="user-123")
-
-    model_client = OpenAIChatCompletionClient(model="gpt-4o")
-    tools = create_hindsight_tools(client=client, bank_id="user-123")
-
-    agent = AssistantAgent(
-        name="assistant",
-        model_client=model_client,
-        tools=tools,
-    )
-
-    # Store a memory
-    result = await agent.run(task="Remember that I prefer dark mode")
-    print(result.messages[-1].content)
-
-    # Hindsight processes retained content asynchronously (fact extraction,
-    # entity resolution, embeddings). A brief pause ensures memories are
-    # searchable before the next recall. In production, this delay is only
-    # needed when retain and recall happen back-to-back in the same script.
-    await asyncio.sleep(3)
-
-    # Recall it later
-    result = await agent.run(task="What are my UI preferences?")
-    print(result.messages[-1].content)
-
-    # Clean up
-    await client.aclose()
-    await model_client.close()
-
-asyncio.run(main())
-```
-
-:::tip Jupyter Notebooks
-If you're running in a Jupyter notebook, you don't need `asyncio.run()` — just use `await` directly in cells since the notebook already has an active event loop.
-:::
-
-The agent gets three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing a client to every call, configure once:
-
-```python
-from hindsight_autogen import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode
-)
-
-# Now create tools without passing client — uses global config
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Memory Scoping with Tags
-
-Use tags to partition memories by topic, session, or user:
-
-```python
-# Store memories tagged by source
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    tags=["source:chat", "session:abc"],
-    recall_tags=["source:chat"],
-    recall_tags_match="any",
-)
-```
-
-## Production Patterns
-
-### Error Handling
-
-Tools raise `HindsightError` on failure, which AutoGen surfaces to the agent as a tool error. Wrap agent calls for graceful degradation:
-
-```python
-from hindsight_autogen.errors import HindsightError
-
-try:
-    result = await agent.run(task="What do you remember about me?")
-except HindsightError as e:
-    print(f"Memory operation failed: {e}")
-```
-
-### Bank Lifecycle
-
-Create banks before first use and clean up when done:
-
-```python
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-
-    # Create bank (idempotent)
-    await client.acreate_bank(bank_id="user-123")
-
-    tools = create_hindsight_tools(client=client, bank_id="user-123")
-    # ... use tools ...
-
-    # Optional: delete bank when no longer needed
-    await client.adelete_bank(bank_id="user-123")
-```
-
-### Multi-Agent Teams
-
-Give each agent its own memory bank, or share a bank across a team:
-
-```python
-# Per-agent memory
-researcher_tools = create_hindsight_tools(client=client, bank_id="researcher-memory")
-writer_tools = create_hindsight_tools(client=client, bank_id="writer-memory")
-
-# Shared team memory
-shared_tools = create_hindsight_tools(
-    client=client,
-    bank_id="team-shared",
-    tags=["team:content"],
-)
-```
-
-## API Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode (any/all/any\_strict/all\_strict) |
-| `retain_metadata` | `None` | Default metadata dict for retain operations |
-| `retain_document_id` | `None` | Default document\_id for retain (groups/upserts memories) |
-| `recall_types` | `None` | Fact types to filter (world, experience, opinion, observation) |
-| `recall_include_entities` | `False` | Include entity information in recall results |
-| `reflect_context` | `None` | Additional context for reflect operations |
-| `reflect_max_tokens` | `None` | Max tokens for reflect results (defaults to `max_tokens`) |
-| `reflect_response_schema` | `None` | JSON schema to constrain reflect output format |
-| `reflect_tags` | `None` | Tags to filter memories used in reflect (defaults to `recall_tags`) |
-| `reflect_tags_match` | `None` | Tag matching for reflect (defaults to `recall_tags_match`) |
-| `include_retain` | `True` | Include the retain (store) tool |
-| `include_recall` | `True` | Include the recall (search) tool |
-| `include_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-
-## Requirements
-
- Python >= 3.10
- autogen-core >= 0.4.0
- hindsight-client >= 0.4.0
@@ -1,167 +0,0 @@
---
-sidebar_position: 5
-title: "Vercel Chat SDK Persistent Memory with Hindsight | Integration"
-description: "Give your Vercel Chat SDK bot persistent, per-user memory across Slack, Discord, Teams, and more. Single handler wrapper, no custom plumbing required."
---
-
-# Vercel Chat SDK
-
-We built `@vectorize-io/hindsight-chat` to give [Vercel Chat SDK](https://github.com/vercel/chat) bots persistent, per-user memory with a single handler wrapper. The integration works across Slack, Discord, Teams, Google Chat, GitHub, and Linear — no custom plumbing required.
-
-[View Changelog →](../../changelog/integrations/chat.md)
-
-## Installation
-
-```bash
-npm install @vectorize-io/hindsight-chat
-```
-
-## Quick Start
-
-```typescript
-import { Chat } from 'chat';
-import { HindsightClient } from '@vectorize-io/hindsight-client';
-import { withHindsightChat } from '@vectorize-io/hindsight-chat';
-import { streamText } from 'ai';
-import { openai } from '@ai-sdk/openai';
-
-const chat = new Chat({ connectors: [/* your connectors */] });
-const hindsight = new HindsightClient({ apiKey: process.env.HINDSIGHT_API_KEY });
-
-chat.onNewMention(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId, // per-user memory
-    },
-    async (thread, message, ctx) => {
-      await thread.subscribe();
-
-      const result = await streamText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-
-      // Stream the response
-      const chunks: string[] = [];
-      for await (const chunk of result.textStream) {
-        chunks.push(chunk);
-      }
-      const fullResponse = chunks.join('');
-      await thread.post(fullResponse);
-
-      // Store the conversation in memory
-      await ctx.retain(
-        `User: ${message.text}\nAssistant: ${fullResponse}`
-      );
-    }
-  )
-);
-```
-
-## Configuration
-
-### `withHindsightChat(options, handler)`
-
-`withHindsightChat` wraps your existing Chat SDK handler and injects memory context automatically. It returns a standard handler `(thread, message) => Promise<void>` so it drops in without changing your handler signature.
-
-#### Options
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `client` | `HindsightClient` | *required* | Hindsight client instance |
-| `bankId` | `string \| (msg) => string` | *required* | Memory bank ID or resolver function |
-| `recall.enabled` | `boolean` | `true` | Auto-recall memories before handler |
-| `recall.budget` | `'low' \| 'mid' \| 'high'` | `'mid'` | Processing budget for recall |
-| `recall.maxTokens` | `number` | API default | Max tokens for recall results |
-| `recall.types` | `FactType[]` | all | Filter to specific fact types |
-| `recall.includeEntities` | `boolean` | `true` | Include entity observations |
-| `retain.enabled` | `boolean` | `false` | Auto-retain inbound messages |
-| `retain.async` | `boolean` | `true` | Fire-and-forget retain |
-| `retain.tags` | `string[]` | – | Tags for retained memories |
-| `retain.metadata` | `Record<string, string>` | – | Metadata for retained memories |
-
-### Context (`ctx`)
-
-We inject a third `ctx` argument into your handler that exposes the full Hindsight memory API scoped to the current user's bank:
-
-| Property/Method | Description |
-|----------------|-------------|
-| `ctx.bankId` | Resolved bank ID |
-| `ctx.memories` | Array of recalled memories |
-| `ctx.entities` | Entity observations (or null) |
-| `ctx.memoriesAsSystemPrompt(options?)` | Format memories for LLM system prompt |
-| `ctx.retain(content, options?)` | Store content in memory |
-| `ctx.recall(query, options?)` | Search memories |
-| `ctx.reflect(query, options?)` | Reason over memories |
-
-## Examples
-
-### Subscribed Message Handler
-
-```typescript
-chat.onSubscribedMessage(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId,
-      recall: { budget: 'high', maxTokens: 1000 },
-    },
-    async (thread, message, ctx) => {
-      const result = await generateText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-      await thread.post(result.text);
-    }
-  )
-);
-```
-
-### Auto-Retain Inbound Messages
-
-```typescript
-chat.onNewMention(
-  withHindsightChat(
-    {
-      client: hindsight,
-      bankId: (msg) => msg.author.userId,
-      retain: { enabled: true, tags: ['slack', 'inbound'] },
-    },
-    async (thread, message, ctx) => {
-      // Inbound message is already being retained automatically
-      const result = await generateText({
-        model: openai('gpt-4o'),
-        system: ctx.memoriesAsSystemPrompt(),
-        messages: [{ role: 'user', content: message.text }],
-      });
-      await thread.post(result.text);
-
-      // Retain the assistant response separately
-      await ctx.retain(`Assistant: ${result.text}`, {
-        tags: ['slack', 'outbound'],
-      });
-    }
-  )
-);
-```
-
-### Static Bank ID (Shared Memory)
-
-```typescript
-// All users share the same memory bank
-chat.onNewMention(
-  withHindsightChat(
-    { client: hindsight, bankId: 'shared-team-memory' },
-    async (thread, message, ctx) => {
-      // ...
-    }
-  )
-);
-```
-
-## Error Handling
-
-We designed the integration so that memory failures never break your bot. Auto-recall and auto-retain errors are caught internally, logged as warnings, and the handler continues with empty memories. Manual `ctx.retain()`, `ctx.recall()`, and `ctx.reflect()` calls propagate errors normally so you can handle them as needed.
@@ -1,216 +0,0 @@
---
-sidebar_position: 5
-title: "Claude Code Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Claude Code with Hindsight. Automatically captures conversations and recalls relevant context across sessions using Claude Code's hook-based architecture."
---
-
-# Claude Code
-
-Biomimetic long-term memory for [Claude Code](https://docs.anthropic.com/en/docs/claude-code) using [Hindsight](https://vectorize.io/hindsight). Automatically captures conversations and intelligently recalls relevant context — a complete port of [`hindsight-openclaw`](./openclaw) adapted to Claude Code's hook-based plugin architecture.
-
-[View Changelog →](../../changelog/integrations/claude-code.md)
-
-## Quick Start
-
-```bash
-# 1. Add the Hindsight marketplace and install the plugin
-claude plugin marketplace add vectorize-io/hindsight
-claude plugin install hindsight-memory
-
-# 2. Configure your LLM provider for memory extraction
-# Option A: OpenAI (auto-detected)
-export OPENAI_API_KEY="sk-your-key"
-
-# Option B: Anthropic (auto-detected)
-export ANTHROPIC_API_KEY="your-key"
-
-# Option C: No API key needed (uses Claude Code's own model — personal/local use only)
-export HINDSIGHT_LLM_PROVIDER=claude-code
-
-# Option D: Connect to an external Hindsight server instead of running locally
-mkdir -p ~/.hindsight
-echo '{"hindsightApiUrl": "https://your-hindsight-server.com"}' > ~/.hindsight/claude-code.json
-
-# 3. Start Claude Code — the plugin activates automatically
-claude
-```
-
-That's it! The plugin will automatically start capturing and recalling memories.
-
-## Features
-
- **Auto-recall** — on every user prompt, queries Hindsight for relevant memories and injects them as context (invisible to the chat transcript, visible to Claude)
- **Auto-retain** — after every response (or every N turns), extracts and retains conversation content to Hindsight for long-term storage
- **Daemon management** — can auto-start/stop `hindsight-embed` locally or connect to an external Hindsight server
- **Dynamic bank IDs** — supports per-agent, per-project, or per-session memory isolation
- **Channel-agnostic** — works with Claude Code Channels (Telegram, Discord, Slack) or interactive sessions
- **Zero dependencies** — pure Python stdlib, no pip install required
-
-## Architecture
-
-The plugin uses all four Claude Code hook events:
-
-| Hook | Event | Purpose |
-|------|-------|---------|
-| `session_start.py` | `SessionStart` | Health check — verify Hindsight is reachable |
-| `recall.py` | `UserPromptSubmit` | **Auto-recall** — query memories, inject as `additionalContext` |
-| `retain.py` | `Stop` | **Auto-retain** — extract transcript, POST to Hindsight (async) |
-| `session_end.py` | `SessionEnd` | Cleanup — stop auto-managed daemon if started |
-
-## Connection Modes
-
-### 1. External API (recommended for production)
-
-Connect to a running Hindsight server (cloud or self-hosted). No local LLM needed — the server handles fact extraction.
-
-```json
-{
-  "hindsightApiUrl": "https://your-hindsight-server.com",
-  "hindsightApiToken": "your-token"
-}
-```
-
-### 2. Local Daemon (auto-managed)
-
-The plugin automatically starts and stops `hindsight-embed` via `uvx`. Requires an LLM provider API key for local fact extraction.
-
-Set an LLM provider:
-```bash
-export OPENAI_API_KEY="sk-your-key"
-# or
-export ANTHROPIC_API_KEY="your-key"
-# or
-export HINDSIGHT_LLM_PROVIDER=claude-code # No API key needed
-```
-
-The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_LLM_MODEL`.
-
-### 3. Existing Local Server
-
-If you already have `hindsight-embed` running, leave `hindsightApiUrl` empty and set `apiPort` to match your server's port. The plugin will detect it automatically.
-
-## Configuration
-
-All settings live in `~/.hindsight/claude-code.json`. Every setting can also be overridden via environment variables. The plugin ships with sensible defaults — you only need to configure what you want to change.
-
-**Loading order** (later entries win):
-1. Built-in defaults (hardcoded in the plugin)
-2. Plugin `settings.json` (ships with the plugin, at `CLAUDE_PLUGIN_ROOT/settings.json`)
-3. User config (`~/.hindsight/claude-code.json` — recommended for your overrides)
-4. Environment variables
-
---
-
-### Connection & Daemon
-
-These settings control how the plugin connects to the Hindsight API.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | `HINDSIGHT_API_URL` | `""` (empty) | URL of an external Hindsight API server. When empty, the plugin uses a local daemon instead. |
-| `hindsightApiToken` | `HINDSIGHT_API_TOKEN` | `null` | Authentication token for the external API. Only needed when `hindsightApiUrl` is set. |
-| `apiPort` | `HINDSIGHT_API_PORT` | `9077` | Port used by the local `hindsight-embed` daemon. Change this if you run multiple instances or have a port conflict. |
-| `daemonIdleTimeout` | `HINDSIGHT_DAEMON_IDLE_TIMEOUT` | `0` | Seconds of inactivity before the local daemon shuts itself down. `0` means the daemon stays running until the session ends. |
-| `embedVersion` | `HINDSIGHT_EMBED_VERSION` | `"latest"` | Which version of `hindsight-embed` to install via `uvx`. Pin to a specific version (e.g. `"0.5.2"`) for reproducibility. |
-| `embedPackagePath` | `HINDSIGHT_EMBED_PACKAGE_PATH` | `null` | Local filesystem path to a `hindsight-embed` checkout. When set, the plugin runs from this path instead of installing via `uvx`. Useful for development. |
-
---
-
-### LLM Provider (local daemon only)
-
-These settings configure which LLM the local daemon uses for fact extraction. They are **ignored** when connecting to an external API (the server uses its own LLM configuration).
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `llmProvider` | `HINDSIGHT_LLM_PROVIDER` | auto-detect | Which LLM provider to use. Supported values: `openai`, `anthropic`, `gemini`, `groq`, `ollama`, `openai-codex`, `claude-code`. When omitted, the plugin auto-detects by checking for API key env vars in order: `OPENAI_API_KEY` → `ANTHROPIC_API_KEY` → `GEMINI_API_KEY` → `GROQ_API_KEY`. |
-| `llmModel` | `HINDSIGHT_LLM_MODEL` | provider default | Override the default model for the chosen provider (e.g. `"gpt-4o"`, `"claude-sonnet-4-20250514"`). When omitted, the Hindsight API picks a sensible default for each provider. |
-| `llmApiKeyEnv` | — | provider standard | Name of the environment variable that holds the API key. Normally auto-detected (e.g. `OPENAI_API_KEY` for the `openai` provider). Set this only if your key is in a non-standard env var. |
-
---
-
-### Memory Bank
-
-A **bank** is an isolated memory store — like a separate "brain." These settings control which bank the plugin reads from and writes to.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `bankId` | `HINDSIGHT_BANK_ID` | `"claude_code"` | The bank ID to use when `dynamicBankId` is `false`. All sessions share this single bank. |
-| `bankMission` | `HINDSIGHT_BANK_MISSION` | generic assistant prompt | A short description of the agent's identity and purpose. Sent to Hindsight when creating or updating the bank, and used during recall to contextualize results. |
-| `retainMission` | — | extraction prompt | Instructions for the fact extraction LLM — tells it *what* to extract from conversations (e.g. "Extract technical decisions and user preferences"). |
-| `dynamicBankId` | `HINDSIGHT_DYNAMIC_BANK_ID` | `false` | When `true`, the plugin derives a unique bank ID from context fields (see `dynamicBankGranularity`), giving each combination its own isolated memory. |
-| `dynamicBankGranularity` | — | `["agent", "project"]` | Which context fields to combine when building a dynamic bank ID. Available fields: `agent` (agent name), `project` (working directory), `session` (session ID), `channel` (channel ID), `user` (user ID). |
-| `bankIdPrefix` | — | `""` | A string prepended to all bank IDs — both static and dynamic. Useful for namespacing (e.g. `"prod"` or `"staging"`). |
-| `agentName` | `HINDSIGHT_AGENT_NAME` | `"claude-code"` | Name used for the `agent` field in dynamic bank ID derivation. |
-
---
-
-### Auto-Recall
-
-Auto-recall runs on every user prompt. It queries Hindsight for relevant memories and injects them into Claude's context as invisible `additionalContext` (the user doesn't see them in the chat transcript).
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `HINDSIGHT_AUTO_RECALL` | `true` | Master switch for auto-recall. Set to `false` to disable memory retrieval entirely. |
-| `recallBudget` | `HINDSIGHT_RECALL_BUDGET` | `"mid"` | Controls how hard Hindsight searches for memories. `"low"` = fast, fewer strategies; `"mid"` = balanced; `"high"` = thorough, slower. Affects latency directly. |
-| `recallMaxTokens` | `HINDSIGHT_RECALL_MAX_TOKENS` | `1024` | Maximum number of tokens in the recalled memory block. Lower values reduce context usage but may truncate relevant memories. |
-| `recallTypes` | — | `["world", "experience"]` | Which memory types to retrieve. `"world"` = general facts; `"experience"` = personal experiences; `"observation"` = raw observations. |
-| `recallContextTurns` | `HINDSIGHT_RECALL_CONTEXT_TURNS` | `1` | How many prior conversation turns to include when composing the recall query. `1` = only the latest user message; higher values give more context but may dilute the query. |
-| `recallMaxQueryChars` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | `800` | Maximum character length of the query sent to Hindsight. Longer queries are truncated. |
-| `recallRoles` | — | `["user", "assistant"]` | Which message roles to include when building the recall query from prior turns. |
-| `recallPromptPreamble` | — | built-in string | Text placed above the recalled memories in the injected context block. Customize this to change how Claude interprets the memories. |
-
---
-
-### Auto-Retain
-
-Auto-retain runs after Claude responds. It extracts the conversation transcript and sends it to Hindsight for long-term storage and fact extraction.
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `HINDSIGHT_AUTO_RETAIN` | `true` | Master switch for auto-retain. Set to `false` to disable memory storage entirely. |
-| `retainMode` | `HINDSIGHT_RETAIN_MODE` | `"full-session"` | Retention strategy. `"full-session"` sends the full conversation transcript (with chunking). |
-| `retainEveryNTurns` | — | `10` | How often to retain. `1` = every turn; `10` = every 10th turn. Higher values reduce API calls but delay memory capture. Values > 1 enable **chunked retention** with a sliding window. |
-| `retainOverlapTurns` | — | `2` | When chunked retention fires, this many extra turns from the previous chunk are included for continuity. Total window size = `retainEveryNTurns + retainOverlapTurns`. |
-| `retainRoles` | — | `["user", "assistant"]` | Which message roles to include in the retained transcript. |
-| `retainToolCalls` | — | `true` | Whether to include tool calls (function invocations and results) in the retained transcript. Captures structured actions like file reads, searches, and code edits. |
-| `retainTags` | — | `["{session_id}"]` | Tags attached to the retained document. Supports `{session_id}` placeholder which is replaced with the current session ID at runtime. |
-| `retainMetadata` | — | `{}` | Arbitrary key-value metadata attached to the retained document. |
-| `retainContext` | — | `"claude-code"` | A label attached to retained memories identifying their source. Useful when multiple integrations write to the same bank. |
-
---
-
-### Debug
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `debug` | `HINDSIGHT_DEBUG` | `false` | Enable verbose logging to stderr. All log lines are prefixed with `[Hindsight]`. Useful for diagnosing connection issues, recall/retain behavior, and bank ID derivation. |
-
-## Claude Code Channels
-
-With [Claude Code Channels](https://docs.anthropic.com/en/docs/claude-code), Claude Code can operate as a persistent background agent connected to Telegram, Discord, Slack, and other messaging platforms. This plugin gives Channel-based agents the same long-term memory that `hindsight-openclaw` provides for Openclaw agents.
-
-For Channel agents, enable dynamic bank IDs for per-channel/per-user memory isolation:
-
-```json
-{
-  "dynamicBankId": true,
-  "dynamicBankGranularity": ["agent", "channel", "user"]
-}
-```
-
-And set channel context via environment variables:
-
-```bash
-export HINDSIGHT_CHANNEL_ID="telegram-group-12345"
-export HINDSIGHT_USER_ID="user-67890"
-```
-
-## Troubleshooting
-
-**Plugin not activating**: Check Claude Code logs for `[Hindsight]` messages. Enable `"debug": true` in `~/.hindsight/claude-code.json`.
-
-**Recall returning no memories**: Verify the Hindsight server is reachable (`curl http://localhost:9077/health`). Memories need at least one retain cycle before they're available.
-
-**Daemon not starting**: Ensure an LLM API key is set (or use `HINDSIGHT_LLM_PROVIDER=claude-code`). Review daemon logs at `~/.hindsight/profiles/claude-code.log`.
-
-**High latency on recall**: The recall hook has a 12-second timeout. Use `recallBudget: "low"` or reduce `recallMaxTokens` for faster responses.
@@ -1,184 +0,0 @@
---
-sidebar_position: 6
-title: "Codex CLI Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to OpenAI Codex CLI with Hindsight. Three Python hook scripts automatically recall context before each prompt and retain conversations — no workflow changes required."
---
-
-# Codex
-
-[View Changelog →](../../changelog/integrations/codex.md)
-
-Persistent memory for [Codex CLI](https://github.com/openai/codex) using [Hindsight](https://vectorize.io/hindsight). Three Python hook scripts automatically recall relevant context before each prompt and retain conversations after each turn — no changes to your Codex workflow required.
-
-## Quick Start
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-codex | bash
-```
-
-The installer will guide you through choosing local or cloud mode and configuring your connection. Once installed, start a new Codex session — memory is live.
-
-To uninstall:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-codex | bash -s -- --uninstall
-```
-
-## Features
-
- **Auto-recall** — on every user prompt, queries Hindsight for relevant memories and injects them as `additionalContext` (invisible to the transcript, visible to Codex)
- **Auto-retain** — after each Codex response, stores the conversation transcript to Hindsight for future recall
- **Dynamic bank IDs** — supports per-project memory isolation based on the working directory
- **Session-level upsert** — uses the session ID as the document ID so re-running the same session updates rather than duplicates stored content
- **Zero dependencies** — pure Python stdlib, no pip install required
-
-## Architecture
-
-The plugin uses three Codex hook events:
-
-| Hook | Event | Purpose |
-|------|-------|---------|
-| `session_start.py` | `SessionStart` | Warm up — verify Hindsight is reachable |
-| `recall.py` | `UserPromptSubmit` | **Auto-recall** — query memories, inject as `additionalContext` |
-| `retain.py` | `Stop` | **Auto-retain** — extract transcript, POST to Hindsight (async) |
-
-On `UserPromptSubmit`, the hook reads the prompt, queries Hindsight for the most relevant memories, and outputs a `hookSpecificOutput.additionalContext` block. Codex prepends this to the conversation before sending it to the model:
-
-```
-<hindsight_memories>
-Relevant memories from past conversations...
-Current time - 2026-03-27 09:14
-
- Project uses FastAPI with asyncpg — not SQLAlchemy [world] (2026-03-26)
- Preferred testing framework: pytest with pytest-asyncio [experience] (2026-03-26)
-</hindsight_memories>
-```
-
-On `Stop`, the hook reads the session transcript, strips previously injected memory tags (to prevent feedback loops), and POSTs the conversation to Hindsight asynchronously.
-
-## Connection Modes
-
-### 1. External API (recommended)
-
-Connect to a running Hindsight server (cloud or self-hosted):
-
-```json
-{
-  "hindsightApiUrl": "https://api.hindsight.vectorize.io",
-  "hindsightApiToken": "hsk_your_token"
-}
-```
-
-### 2. Local Daemon
-
-Run `hindsight-embed` locally. The `session_start.py` hook will detect it on `apiPort` (default `9077`). The daemon is not auto-started by the Codex plugin — start it separately:
-
-```bash
-uvx hindsight-embed
-```
-
-Then leave `hindsightApiUrl` empty in your config and the plugin will connect to `http://localhost:9077`.
-
-## Configuration
-
-Settings are loaded from `~/.hindsight/codex.json`. Every setting can also be overridden via environment variable.
-
-**Loading order** (later entries win):
-
-1. Built-in defaults
-2. Plugin `settings.json` (at `~/.hindsight/codex/settings.json`)
-3. User config (`~/.hindsight/codex.json`)
-4. Environment variables
-
---
-
-### Connection
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | `HINDSIGHT_API_URL` | `""` | URL of the Hindsight API server. Required. |
-| `hindsightApiToken` | `HINDSIGHT_API_TOKEN` | `null` | API token for authentication. Required for Hindsight Cloud. |
-| `apiPort` | `HINDSIGHT_API_PORT` | `9077` | Port for the local `hindsight-embed` daemon. |
-
---
-
-### Memory Bank
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `bankId` | `HINDSIGHT_BANK_ID` | `"codex"` | The bank to read from and write to. All sessions share this bank unless `dynamicBankId` is enabled. |
-| `bankMission` | `HINDSIGHT_BANK_MISSION` | coding assistant prompt | Describes the agent's purpose. Sent when creating or updating the bank. |
-| `retainMission` | — | extraction prompt | Instructions for Hindsight's fact extraction — what to extract from coding conversations. |
-| `dynamicBankId` | `HINDSIGHT_DYNAMIC_BANK_ID` | `false` | When `true`, derives a unique bank ID from `dynamicBankGranularity` fields — useful for per-project isolation. |
-| `dynamicBankGranularity` | — | `["agent", "project"]` | Which fields to combine for dynamic bank IDs. `"project"` = working directory, `"agent"` = agent name. |
-| `bankIdPrefix` | — | `""` | Prefix prepended to all bank IDs. |
-| `agentName` | `HINDSIGHT_AGENT_NAME` | `"codex"` | Agent name used in dynamic bank ID derivation. |
-
---
-
-### Auto-Recall
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `HINDSIGHT_AUTO_RECALL` | `true` | Master switch for auto-recall. |
-| `recallBudget` | `HINDSIGHT_RECALL_BUDGET` | `"mid"` | Search depth: `"low"` (fast), `"mid"` (balanced), `"high"` (thorough). |
-| `recallMaxTokens` | `HINDSIGHT_RECALL_MAX_TOKENS` | `1024` | Max tokens in the recalled memory block. |
-| `recallTypes` | — | `["world", "experience"]` | Memory types to retrieve. |
-| `recallContextTurns` | `HINDSIGHT_RECALL_CONTEXT_TURNS` | `1` | Prior turns to include when building the recall query. `1` = latest prompt only. |
-| `recallMaxQueryChars` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | `800` | Max characters in the query sent to Hindsight. |
-| `recallRoles` | — | `["user", "assistant"]` | Which roles to include when building a multi-turn query. |
-| `recallPromptPreamble` | — | built-in | Text placed above the recalled memories in the injected context block. |
-
---
-
-### Auto-Retain
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `HINDSIGHT_AUTO_RETAIN` | `true` | Master switch for auto-retain. |
-| `retainMode` | `HINDSIGHT_RETAIN_MODE` | `"full-session"` | `"full-session"` sends the full transcript per session (upserted by session ID). `"chunked"` sends sliding windows every N turns. |
-| `retainEveryNTurns` | — | `10` | Retain fires every N turns. `1` = every turn. Higher values reduce API calls. |
-| `retainOverlapTurns` | — | `2` | Extra turns included from the previous chunk (chunked mode only). |
-| `retainRoles` | — | `["user", "assistant"]` | Which roles to include in the retained transcript. |
-| `retainTags` | — | `["{session_id}"]` | Tags attached to the stored document. `{session_id}` is replaced at runtime. |
-| `retainMetadata` | — | `{}` | Arbitrary key-value metadata attached to the stored document. |
-| `retainContext` | — | `"codex"` | Label identifying the source integration. Useful when multiple integrations write to the same bank. |
-
---
-
-### Debug
-
-| Setting | Env Var | Default | Description |
-|---------|---------|---------|-------------|
-| `debug` | `HINDSIGHT_DEBUG` | `false` | Enable verbose logging to stderr. All log lines are prefixed with `[Hindsight]`. |
-
-## Per-Project Memory
-
-To give each project its own isolated memory bank, enable dynamic bank IDs:
-
-```json
-{
-  "dynamicBankId": true,
-  "dynamicBankGranularity": ["agent", "project"]
-}
-```
-
-With this config, running Codex in `~/projects/api` and `~/projects/frontend` stores and recalls memories separately. Bank IDs are derived from the working directory path.
-
-## Troubleshooting
-
-**Hooks not firing**: Check that `~/.codex/config.toml` contains `codex_hooks = true` under `[features]`. Re-run the installer to fix this automatically.
-
-**No memories recalled**: Recall returns results only after something has been retained. Either complete one Codex session first, or seed your bank manually using the [cookbook example](https://github.com/vectorize-io/hindsight-cookbook/tree/main/applications/codex-memory).
-
-**Memory not being stored**: `retainEveryNTurns` defaults to `10` — retain only fires every 10 turns. While testing, add `"retainEveryNTurns": 1` to `~/.hindsight/codex.json`.
-
-**Debug mode**: Add `"debug": true` to `~/.hindsight/codex.json` to see what Hindsight is doing on each turn:
-
-```
-[Hindsight] Recalling from bank 'codex', query length: 42
-[Hindsight] Injecting 3 memories
-[Hindsight] Retaining to bank 'codex', doc 'sess-abc123', 2 messages, 847 chars
-```
-
-**High latency on recall**: Use `"recallBudget": "low"` or reduce `recallMaxTokens` to speed up recall queries.
@@ -1,245 +0,0 @@
---
-sidebar_position: 5
-title: "CrewAI Persistent Memory with Hindsight | Integration Guide"
-description: "Add long-term memory to your CrewAI agent crews. Hindsight provides fact extraction, entity tracking, and temporal awareness — persisted automatically across all crew runs."
---
-
-# CrewAI
-
-Persistent memory for AI agent crews via [CrewAI](https://github.com/crewAIInc/crewAI). Give your crews long-term memory with fact extraction, entity tracking, and temporal awareness.
-
-[View Changelog →](../../changelog/integrations/crewai.md)
-
-## Features
-
- **Drop-in Storage Backend** - Implements CrewAI's `Storage` interface for `ExternalMemory`
- **Automatic Memory Flow** - CrewAI automatically stores task outputs and retrieves relevant memories
- **Per-Agent Banks** - Optionally give each agent its own isolated memory bank
- **Reflect Tool** - Agents can explicitly reason over memories with disposition-aware synthesis
- **Simple Configuration** - Configure once, use everywhere
-
-## Installation
-
-```bash
-pip install hindsight-crewai
-```
-
-## Quick Start
-
-```python
-from hindsight_crewai import configure, HindsightStorage
-from crewai.memory.external.external_memory import ExternalMemory
-from crewai import Agent, Crew, Task
-
-configure(hindsight_api_url="http://localhost:8888")
-
-crew = Crew(
-    agents=[Agent(role="Researcher", goal="Find information", backstory="...")],
-    tasks=[Task(description="Research AI trends", expected_output="Report")],
-    external_memory=ExternalMemory(
-        storage=HindsightStorage(bank_id="my-crew")
-    ),
-)
-
-crew.kickoff()
-```
-
-That's it. CrewAI will automatically:
- **Query memories** at the start of each task
- **Store task outputs** to Hindsight after each task completes
-
-Memories persist across crew runs, so your crew learns over time.
-
-## How It Works
-
-The integration maps CrewAI's 3-method `Storage` interface to Hindsight's API:
-
-| CrewAI | Hindsight | What happens |
-|--------|-----------|--------------|
-| `save(value, metadata, agent)` | `retain(bank_id, content, ...)` | Task output is stored. Hindsight extracts facts, entities, and relationships from the raw text. |
-| `search(query, limit)` | `recall(bank_id, query, ...)` | CrewAI constructs a query from the task description. Hindsight runs semantic search, BM25, graph traversal, and reranking. |
-| `reset()` | `delete_bank(bank_id)` | Wipes the bank and optionally recreates it with its original mission. |
-
-CrewAI calls `search()` automatically at the start of each task and `save()` after each task completes.
-
-## Configuration Options
-
-```python
-from hindsight_crewai import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",  # Hindsight API URL
-    api_key="your-api-key",                     # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                               # Recall budget: "low", "mid", "high"
-    max_tokens=4096,                            # Max tokens for recall results
-    tags=["env:prod"],                          # Tags for stored memories
-    recall_tags=["scope:global"],               # Tags to filter recall
-    recall_tags_match="any",                    # Tag match: any/all/any_strict/all_strict
-    verbose=True,                               # Enable logging
-)
-```
-
-### Per-Storage Overrides
-
-Constructor arguments override global configuration:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    budget="high",
-    max_tokens=8192,
-    tags=["team:alpha"],
-)
-```
-
-## Bank Missions
-
-Set a mission to guide how Hindsight processes and organizes memories:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    mission="Track software architecture decisions, technical debt, and team preferences.",
-)
-```
-
-## Per-Agent Memory Banks
-
-Give each agent its own isolated memory bank:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    per_agent_banks=True,
-    # Researcher -> "my-crew-researcher"
-    # Writer     -> "my-crew-writer"
-)
-```
-
-Or use a custom bank resolver for full control:
-
-```python
-storage = HindsightStorage(
-    bank_id="my-crew",
-    bank_resolver=lambda base, agent: f"{base}-{agent.lower()}" if agent else base,
-)
-```
-
-:::info
-When `per_agent_banks=True`, the automatic `search()` at task start queries the base bank (shared context), since CrewAI's `search()` method does not receive the agent parameter. For per-agent search isolation, create separate `HindsightStorage` instances per agent.
-:::
-
-## Reflect Tool
-
-CrewAI's storage interface only supports save/search/reset. To give agents access to Hindsight's `reflect` (disposition-aware memory synthesis), add it as a tool:
-
-```python
-from hindsight_crewai import HindsightReflectTool
-
-reflect_tool = HindsightReflectTool(
-    bank_id="my-crew",
-    budget="mid",
-    reflect_context="You are helping a software team track decisions.",
-)
-
-agent = Agent(
-    role="Analyst",
-    goal="Analyze project history",
-    backstory="...",
-    tools=[reflect_tool],
-)
-```
-
-When the agent calls this tool, it gets a synthesized, contextual answer based on all relevant memories rather than raw fact snippets.
-
-## Full Example
-
-A research crew that remembers findings across runs:
-
-```python
-from hindsight_crewai import configure, HindsightStorage, HindsightReflectTool
-from crewai.memory.external.external_memory import ExternalMemory
-from crewai import Agent, Crew, Task
-
-configure(hindsight_api_url="http://localhost:8888")
-
-storage = HindsightStorage(
-    bank_id="research-crew",
-    mission="Track technology research findings and comparisons.",
-)
-
-reflect_tool = HindsightReflectTool(bank_id="research-crew", budget="mid")
-
-researcher = Agent(
-    role="Researcher",
-    goal="Research topics, building on prior knowledge.",
-    backstory="Before starting, use hindsight_reflect to check what you already know.",
-    tools=[reflect_tool],
-)
-
-writer = Agent(
-    role="Writer",
-    goal="Write summaries incorporating prior findings.",
-    backstory="Use hindsight_reflect to recall prior research.",
-    tools=[reflect_tool],
-)
-
-crew = Crew(
-    agents=[researcher, writer],
-    tasks=[
-        Task(description="Research the benefits of Rust", expected_output="Analysis", agent=researcher),
-        Task(description="Write an executive summary", expected_output="Summary", agent=writer),
-    ],
-    external_memory=ExternalMemory(storage=storage),
-)
-
-# Run 1: researches Rust, stores findings
-crew.kickoff()
-
-# Run 2: recalls Rust research when comparing with Go
-crew.tasks[0].description = "Compare Rust with Go"
-crew.kickoff()
-```
-
-## API Reference
-
-### Configuration
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Set global connection and default settings |
-| `get_config()` | Get current configuration |
-| `reset_config()` | Reset configuration to None |
-
-### Storage
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `hindsight_api_url` | from config | Override API URL |
-| `api_key` | from config | Override API key |
-| `budget` | `"mid"` | Recall budget (low/mid/high) |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `tags` | `None` | Tags applied when storing |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `per_agent_banks` | `False` | Give each agent its own bank |
-| `bank_resolver` | `None` | Custom `(bank_id, agent) -> bank_id` |
-| `mission` | `None` | Bank mission for memory organization |
-| `verbose` | `False` | Enable verbose logging |
-
-### Reflect Tool
-
-| Parameter | Default | Description |
-|-----------|---------|-------------|
-| `bank_id` | required | Hindsight memory bank ID |
-| `budget` | `"mid"` | Reflect budget (low/mid/high) |
-| `reflect_context` | `None` | Additional context for reasoning |
-| `hindsight_api_url` | from config | Override API URL |
-| `api_key` | from config | Override API key |
-
-## Requirements
-
- Python >= 3.10
- crewai >= 0.86.0
- A running Hindsight API server
@@ -1,177 +0,0 @@
---
-sidebar_position: 10
-title: "Hermes Agent Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Hermes Agent with Hindsight. Automatically recalls context before every LLM call and retains conversations for future sessions."
---
-
-# Hermes Agent
-
-Persistent long-term memory for [Hermes Agent](https://github.com/NousResearch/hermes-agent) using [Hindsight](https://vectorize.io/hindsight). Automatically recalls relevant context before every LLM call and retains conversations for future sessions — plus explicit retain/recall/reflect tools.
-
-## Quick Start
-
-```bash
-# 1. Install the plugin into Hermes's Python environment
-uv pip install hindsight-hermes --python $HOME/.hermes/hermes-agent/venv/bin/python
-
-# 2. Configure (choose one)
-# Option A: Config file (recommended)
-mkdir -p ~/.hindsight
-cat > ~/.hindsight/hermes.json << 'EOF'
-{
-  "hindsightApiUrl": "http://localhost:9077",
-  "bankId": "hermes"
-}
-EOF
-
-# Option B: Environment variables
-export HINDSIGHT_API_URL=http://localhost:9077
-export HINDSIGHT_BANK_ID=hermes
-
-# 3. Start Hermes — the plugin activates automatically
-hermes
-```
-
-## Features
-
- **Auto-recall** — on every turn, queries Hindsight for relevant memories and injects them into the system prompt (via `pre_llm_call` hook)
- **Auto-retain** — after every response, retains the user/assistant exchange to Hindsight (via `post_llm_call` hook)
- **Explicit tools** — `hindsight_retain`, `hindsight_recall`, `hindsight_reflect` for direct model control
- **Config file** — `~/.hindsight/hermes.json` with the same field names as openclaw and claude-code integrations
- **Zero config overhead** — env vars still work as overrides for CI/automation
-
-:::note
-The lifecycle hooks (`pre_llm_call`/`post_llm_call`) require hermes-agent with [PR #2823](https://github.com/NousResearch/hermes-agent/pull/2823) or later. On older versions, only the three tools are registered — hooks are silently skipped.
-:::
-
-## Architecture
-
-The plugin registers via Hermes's `hermes_agent.plugins` entry point system:
-
-| Component | Purpose |
-|-----------|---------|
-| `pre_llm_call` hook | **Auto-recall** — query memories, inject as ephemeral system prompt context |
-| `post_llm_call` hook | **Auto-retain** — store user/assistant exchange to Hindsight |
-| `hindsight_retain` tool | Explicit memory storage (model-initiated) |
-| `hindsight_recall` tool | Explicit memory search (model-initiated) |
-| `hindsight_reflect` tool | LLM-synthesized answer from stored memories |
-
-## Connection Modes
-
-### 1. External API (recommended for production)
-
-Connect to a running Hindsight server (cloud or self-hosted). No local LLM needed — the server handles fact extraction.
-
-```json
-{
-  "hindsightApiUrl": "https://your-hindsight-server.com",
-  "hindsightApiToken": "your-token",
-  "bankId": "hermes"
-}
-```
-
-### 2. Local Daemon
-
-If you're running `hindsight-embed` locally, point to it:
-
-```json
-{
-  "hindsightApiUrl": "http://localhost:9077",
-  "bankId": "hermes"
-}
-```
-
-Follow the [Quick Start](../../developer/api/quickstart.md) guide to get the Hindsight API running.
-
-## Configuration
-
-All settings are in `~/.hindsight/hermes.json`. Every setting can also be overridden via environment variables (env vars take priority).
-
-### Connection & Daemon
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `hindsightApiUrl` | — | `HINDSIGHT_API_URL` | Hindsight API URL |
-| `hindsightApiToken` | `null` | `HINDSIGHT_API_TOKEN` / `HINDSIGHT_API_KEY` | Auth token for API |
-| `apiPort` | `9077` | `HINDSIGHT_API_PORT` | Port for local Hindsight daemon |
-| `daemonIdleTimeout` | `0` | `HINDSIGHT_DAEMON_IDLE_TIMEOUT` | Seconds before idle daemon shuts down (0 = never) |
-| `embedVersion` | `"latest"` | `HINDSIGHT_EMBED_VERSION` | `hindsight-embed` version for `uvx` |
-
-### LLM Provider (daemon mode only)
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `llmProvider` | auto-detect | `HINDSIGHT_LLM_PROVIDER` | LLM provider: `openai`, `anthropic`, `gemini`, `groq`, `ollama` |
-| `llmModel` | provider default | `HINDSIGHT_LLM_MODEL` | Model override |
-
-### Memory Bank
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `bankId` | — | `HINDSIGHT_BANK_ID` | Memory bank ID |
-| `bankMission` | `""` | `HINDSIGHT_BANK_MISSION` | Agent identity/purpose for the memory bank |
-| `retainMission` | `null` | — | Custom retain mission (what to extract from conversations) |
-| `bankIdPrefix` | `""` | — | Prefix for all bank IDs |
-
-### Auto-Recall
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `autoRecall` | `true` | `HINDSIGHT_AUTO_RECALL` | Enable automatic memory recall via `pre_llm_call` hook |
-| `recallBudget` | `"mid"` | `HINDSIGHT_RECALL_BUDGET` | Recall effort: `low`, `mid`, `high` |
-| `recallMaxTokens` | `4096` | `HINDSIGHT_RECALL_MAX_TOKENS` | Max tokens in recall response |
-| `recallMaxQueryChars` | `800` | `HINDSIGHT_RECALL_MAX_QUERY_CHARS` | Max chars of user message used as query |
-| `recallPromptPreamble` | see below | — | Header text injected before recalled memories |
-
-Default preamble:
-> Relevant memories from past conversations (prioritize recent when conflicting). Only use memories that are directly useful to continue this conversation; ignore the rest:
-
-### Auto-Retain
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `autoRetain` | `true` | `HINDSIGHT_AUTO_RETAIN` | Enable automatic retention via `post_llm_call` hook |
-| `retainEveryNTurns` | `1` | — | Retain every Nth turn |
-| `retainOverlapTurns` | `2` | — | Extra overlap turns for continuity |
-| `retainRoles` | `["user", "assistant"]` | — | Which message roles to retain |
-
-### Miscellaneous
-
-| Setting | Default | Env Var | Description |
-|---------|---------|---------|-------------|
-| `debug` | `false` | `HINDSIGHT_DEBUG` | Enable debug logging to stderr |
-
-## Hermes Gateway (Telegram, Discord, Slack)
-
-When using Hermes in gateway mode (multi-platform messaging), the plugin works across all platforms. Hermes creates a fresh `AIAgent` per message, and the plugin's `pre_llm_call` hook ensures relevant memories are recalled for each turn regardless of platform.
-
-## Disabling Hermes's Built-in Memory
-
-Hermes has a built-in `memory` tool that saves to local markdown files. If both are active, the LLM may prefer the built-in one. Disable it:
-
-```bash
-hermes tools disable memory
-```
-
-Re-enable later with `hermes tools enable memory`.
-
-## Troubleshooting
-
-**Plugin not loading**: Verify the entry point is registered:
-```bash
-python -c "
-import importlib.metadata
-eps = importlib.metadata.entry_points(group='hermes_agent.plugins')
-print(list(eps))
-"
-```
-You should see `EntryPoint(name='hindsight', value='hindsight_hermes', ...)`.
-
-**Tools don't appear in `/tools`**: Check that `hindsightApiUrl` (or `HINDSIGHT_API_URL`) is set. The plugin silently skips registration when unconfigured.
-
-**Connection refused**: Verify the Hindsight API is running:
-```bash
-curl http://localhost:9077/health
-```
-
-**Recall returning no memories**: Memories need at least one retain cycle. Try storing a fact first, then asking about it in a new session.
@@ -1,319 +0,0 @@
---
-sidebar_position: 7
-title: "LangGraph & LangChain Persistent Memory with Hindsight"
-description: "Add long-term memory to LangGraph and LangChain agents with Hindsight. Three integration patterns — tools, nodes, and BaseStore adapter — for persistent memory across agent runs."
---
-
-# LangGraph / LangChain
-
-Persistent long-term memory for [LangGraph](https://langchain-ai.github.io/langgraph/) and [LangChain](https://python.langchain.com/) agents via Hindsight. Three integration patterns at different abstraction levels — the tools pattern works with both LangChain and LangGraph, while nodes and the BaseStore adapter are LangGraph-specific.
-
-[View Changelog →](../../changelog/integrations/langgraph.md)
-
-## Features
-
- **Memory Tools** — retain, recall, and reflect as LangChain `@tool` functions compatible with `bind_tools()` and `ToolNode`. Works with **both LangChain and LangGraph** — no LangGraph dependency required for this pattern.
- **Graph Nodes** *(LangGraph)* — Pre-built nodes that auto-inject memories before LLM calls and auto-store after responses
- **BaseStore Adapter** *(LangGraph)* — Drop-in `BaseStore` implementation backed by Hindsight, for LangGraph's native memory patterns
- **Dynamic Banks** — Resolve bank IDs per-request from `RunnableConfig` for per-user memory
- **Async-Native** — Uses `aretain`, `arecall`, `areflect` directly — no thread-pool workarounds
-
-## Installation
-
-```bash
-pip install hindsight-langgraph
-```
-
-## Quick Start: Tools (LangChain & LangGraph)
-
-The tools pattern creates standard LangChain `@tool` functions that work with any LangChain-compatible model via `bind_tools()`. You can use them with a LangGraph agent or with plain LangChain — no LangGraph required.
-
-**With LangGraph (recommended):**
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_hindsight_tools
-from langchain_openai import ChatOpenAI
-from langgraph.prebuilt import create_react_agent
-
-client = Hindsight(base_url="http://localhost:8888")
-tools = create_hindsight_tools(client=client, bank_id="user-123")
-
-agent = create_react_agent(ChatOpenAI(model="gpt-4o"), tools=tools)
-
-result = await agent.ainvoke(
-    {"messages": [{"role": "user", "content": "Remember that I prefer dark mode"}]}
-)
-```
-
-**With plain LangChain:**
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_hindsight_tools
-from langchain_openai import ChatOpenAI
-
-client = Hindsight(base_url="http://localhost:8888")
-tools = create_hindsight_tools(client=client, bank_id="user-123")
-
-model = ChatOpenAI(model="gpt-4o").bind_tools(tools)
-response = await model.ainvoke("Remember that I prefer dark mode")
-```
-
-When using plain LangChain, you handle the tool execution loop yourself — call the model, check for `tool_calls`, execute them, and feed results back. LangGraph automates this loop for you.
-
-The agent gets three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-## Quick Start: Memory Nodes (LangGraph)
-
-Add recall and retain nodes to your graph for automatic memory injection and storage.
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import create_recall_node, create_retain_node
-from langgraph.graph import StateGraph, MessagesState, START, END
-
-client = Hindsight(base_url="http://localhost:8888")
-
-recall = create_recall_node(client=client, bank_id="user-123")
-retain = create_retain_node(client=client, bank_id="user-123")
-
-builder = StateGraph(MessagesState)
-builder.add_node("recall", recall)
-builder.add_node("agent", agent_node)  # your LLM node
-builder.add_node("retain", retain)
-
-builder.add_edge(START, "recall")
-builder.add_edge("recall", "agent")
-builder.add_edge("agent", "retain")
-builder.add_edge("retain", END)
-
-graph = builder.compile()
-```
-
-The recall node extracts the latest user message, searches Hindsight, and injects matching memories as a `SystemMessage`. The retain node stores human messages (optionally AI messages too) after the response.
-
-## Quick Start: BaseStore (LangGraph)
-
-Use Hindsight as a LangGraph `BaseStore` for cross-thread persistent memory with semantic search.
-
-```python
-from hindsight_client import Hindsight
-from hindsight_langgraph import HindsightStore
-
-client = Hindsight(base_url="http://localhost:8888")
-store = HindsightStore(client=client)
-
-graph = builder.compile(checkpointer=checkpointer, store=store)
-
-# Store and search via the store API
-await store.aput(("user", "123", "prefs"), "theme", {"value": "dark mode"})
-results = await store.asearch(("user", "123", "prefs"), query="theme preference")
-```
-
-Namespace tuples are mapped to Hindsight bank IDs with `.` as separator (e.g., `("user", "123")` becomes bank `user.123`). Banks are auto-created on first access.
-
-## Dynamic Bank IDs
-
-Both nodes and the store support per-user bank resolution from `RunnableConfig`:
-
-```python
-recall = create_recall_node(client=client, bank_id_from_config="user_id")
-retain = create_retain_node(client=client, bank_id_from_config="user_id")
-
-# Bank ID resolved at runtime from config
-result = await graph.ainvoke(
-    {"messages": [{"role": "user", "content": "hello"}]},
-    config={"configurable": {"user_id": "user-456"}},
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing a client to every call, configure once:
-
-```python
-from hindsight_langgraph import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing client — uses global config
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Retain Node Options
-
-```python
-retain = create_retain_node(
-    client=client,
-    bank_id="user-123",
-    retain_human=True,    # Store human messages (default: True)
-    retain_ai=False,      # Store AI responses (default: False)
-    tags=["source:chat"], # Tags applied to stored memories
-)
-```
-
-## Recall Node Options
-
-```python
-recall = create_recall_node(
-    client=client,
-    bank_id="user-123",
-    budget="low",          # Recall budget: low/mid/high
-    max_results=10,        # Max memories injected
-    max_tokens=4096,       # Max tokens for recall
-    tags=["scope:user"],   # Filter by tags
-    tags_match="all",      # Tag match mode
-)
-```
-
-### Using `output_key` for Prompt Control
-
-By default, the recall node appends a `SystemMessage` to `messages`. Use `output_key` to write memory text to a custom state field instead, giving you full control over prompt ordering:
-
-```python
-from typing import Optional
-from langgraph.graph import MessagesState
-
-class AgentState(MessagesState):
-    memory_context: Optional[str] = None
-
-recall = create_recall_node(
-    client=client,
-    bank_id="user-123",
-    output_key="memory_context",
-)
-
-# In your agent node, read state["memory_context"] and prepend it
-# to the system prompt before calling the model.
-```
-
-## Limitations and Notes
-
-### HindsightStore
-
- **Async-only.** All sync methods (`batch`, `get`, `put`, `delete`, `search`, `list_namespaces`) raise `NotImplementedError`. Use the async variants (`abatch`, `aget`, `aput`, `adelete`, `asearch`, `alist_namespaces`) instead.
- **`get()` relies on recall.** There is no direct key lookup — the key is used as a recall query and only exact `document_id` matches are returned. Items that do not rank in the top recall results may appear missing.
- **`list_namespaces` is session-scoped.** It only tracks namespaces that have been written to via `aput()` during the current process. After a restart, `list_namespaces` returns empty even though data still exists in Hindsight.
- **`delete` is a no-op.** Calling `adelete()` logs a debug message but does not remove data from Hindsight. Hindsight's memory model is append-oriented; fact superseding is handled automatically during retain.
-
-### Memory Nodes
-
- **SystemMessage ordering.** The recall node adds a `SystemMessage` with recalled memories. Because `MessagesState` uses `add_messages` (which appends), this message appears after existing messages rather than at position 0. The message has a stable ID (`hindsight_memory_context`) so it is updated rather than duplicated across invocations. If your LLM provider requires system messages first, sort or filter messages in your agent node before passing them to the model.
-
-### Error Handling
-
- **Tools** raise `HindsightError` on failure, which surfaces to the agent as a tool error.
- **Nodes** silently log errors and return empty messages, so a Hindsight outage does not crash your graph.
-
-## API Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode (any/all/any\_strict/all\_strict) |
-| `retain_metadata` | `None` | Default metadata dict for retain operations |
-| `retain_document_id` | `None` | Default document\_id for retain (groups/upserts memories) |
-| `recall_types` | `None` | Fact types to filter (world, experience, opinion, observation) |
-| `recall_include_entities` | `False` | Include entity information in recall results |
-| `reflect_context` | `None` | Additional context for reflect operations |
-| `reflect_max_tokens` | `None` | Max tokens for reflect results (defaults to `max_tokens`) |
-| `reflect_response_schema` | `None` | JSON schema to constrain reflect output format |
-| `reflect_tags` | `None` | Tags to filter memories used in reflect (defaults to `recall_tags`) |
-| `reflect_tags_match` | `None` | Tag matching for reflect (defaults to `recall_tags_match`) |
-| `include_retain` | `True` | Include the retain (store) tool |
-| `include_recall` | `True` | Include the recall (search) tool |
-| `include_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `create_recall_node()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static bank ID (or use `bank_id_from_config`) |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall budget level |
-| `max_tokens` | `4096` | Max tokens for recall results |
-| `max_results` | `10` | Max memories to inject |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-| `bank_id_from_config` | `"user_id"` | Config key to resolve bank ID at runtime |
-| `output_key` | `None` | If set, write memory text to this state key instead of appending a SystemMessage to `messages` |
-
-### `create_retain_node()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | `None` | Static bank ID (or use `bank_id_from_config`) |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `tags` | `None` | Tags applied to stored memories |
-| `bank_id_from_config` | `"user_id"` | Config key to resolve bank ID at runtime |
-| `retain_human` | `True` | Store human messages |
-| `retain_ai` | `False` | Store AI responses |
-
-### `HindsightStore()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `tags` | `None` | Tags applied to all retain operations |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- langchain-core >= 0.3.0
- hindsight-client >= 0.4.0
- langgraph >= 0.3.0 *(only for nodes and store patterns — install with `pip install hindsight-langgraph[langgraph]`)*
@@ -1,349 +0,0 @@
---
-sidebar_position: 1
-title: "LiteLLM Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to any LLM application via LiteLLM and Hindsight. Universal integration — works with any model or provider with just a few lines of code."
---
-
-# LiteLLM
-
-Universal LLM memory integration via [LiteLLM](https://github.com/BerriAI/litellm). Add persistent memory to any LLM application with just a few lines of code.
-
-[View Changelog →](../../changelog/integrations/litellm.md)
-
-## Features
-
- **Universal LLM Support** - Works with 100+ LLM providers via LiteLLM (OpenAI, Anthropic, Groq, Azure, AWS Bedrock, Google Vertex AI, and more)
- **Simple Integration** - Just configure, enable, and use `hindsight_litellm.completion()`
- **Automatic Memory Injection** - Relevant memories are injected into prompts before LLM calls
- **Automatic Conversation Storage** - Conversations are stored to Hindsight for future recall
- **Two Memory Modes** - Choose between `reflect` (synthesized context) or `recall` (raw memory retrieval)
- **Direct Memory APIs** - Query, synthesize, and store memories manually
- **Native Client Wrappers** - Alternative wrappers for OpenAI and Anthropic SDKs
-
-## Installation
-
-```bash
-pip install hindsight-litellm
-```
-
-## Quick Start
-
-```python
-import hindsight_litellm
-
-# Configure and enable memory integration
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# Use the convenience wrapper - memory is automatically injected and stored
-response = hindsight_litellm.completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What did we discuss about AI?"}]
-)
-```
-
-## How It Works
-
-When you call `completion()`, the following happens automatically:
-
-1. **Memory Retrieval** - Hindsight is queried for relevant memories based on the conversation
-2. **Prompt Injection** - Memories are injected into the system message
-3. **LLM Call** - The enriched prompt is sent to the LLM
-4. **Conversation Storage** - The conversation is stored to Hindsight for future recall
-5. **Response Returned** - You receive the response as normal
-
-## Configuration Options
-
-```python
-hindsight_litellm.configure(
-    # Required
-    hindsight_api_url="http://localhost:8888",  # Hindsight API server URL
-    bank_id="my-agent",                          # Memory bank ID
-
-    api_key="your-api-key",        # Optional API key for authentication
-
-    # Optional - Memory behavior
-    store_conversations=True,      # Store conversations after LLM calls
-    inject_memories=True,          # Inject relevant memories into prompts
-    use_reflect=False,             # Use reflect API (synthesized) vs recall (raw memories)
-    reflect_include_facts=False,   # Include source facts with reflect responses
-    max_memories=None,             # Maximum memories to inject (None = unlimited)
-    max_memory_tokens=4096,        # Maximum tokens for memory context
-    recall_budget="mid",           # Recall budget: "low", "mid", "high"
-    fact_types=["world", "agent"], # Filter fact types to inject
-
-    # Optional - Bank Configuration
-    bank_name="My Agent",          # Human-readable display name for the memory bank
-    mission="This agent...",       # Instructions guiding what Hindsight should remember
-
-    # Optional - Advanced
-    injection_mode="system_message",  # or "prepend_user"
-    excluded_models=["gpt-3.5*"],     # Exclude certain models
-    verbose=True,                     # Enable verbose logging and debug info
-)
-```
-
-### Bank Configuration
-
-The `mission` and `bank_name` parameters configure the memory bank itself. When provided, `configure()` will automatically create or update the bank with these settings.
-
-```python
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="support-router",
-    bank_name="Customer Support Router",
-    mission="""You're a customer support router - keep track of which types of issues
-    should go to which teams (billing, technical, sales), customer preferences for
-    communication channels, and past issue resolutions.""",
-)
-```
-
-### Memory Modes: Reflect vs Recall
-
- **Recall mode** (`use_reflect=False`, default): Retrieves raw memory facts and injects them as a numbered list. Best when you need precise, individual memories.
- **Reflect mode** (`use_reflect=True`): Synthesizes memories into a coherent context paragraph. Best for natural, conversational memory context.
-
-```python
-# Recall mode - raw memories
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=False,  # Default
-)
-# Injects: "1. [WORLD] User prefers Python\n2. [MENTAL MODEL] User prefers simple code..."
-
-# Reflect mode - synthesized context
-hindsight_litellm.configure(
-    bank_id="my-agent",
-    use_reflect=True,
-)
-# Injects: "Based on previous conversations, the user is a Python developer who..."
-```
-
-## Multi-Provider Support
-
-Works with any LiteLLM-supported provider:
-
-```python
-import hindsight_litellm
-
-hindsight_litellm.configure(
-    hindsight_api_url="http://localhost:8888",
-    bank_id="my-agent",
-)
-hindsight_litellm.enable()
-
-# OpenAI
-hindsight_litellm.completion(model="gpt-4o", messages=[...])
-
-# Anthropic
-hindsight_litellm.completion(model="claude-3-5-sonnet-20241022", messages=[...])
-
-# Groq
-hindsight_litellm.completion(model="groq/llama-3.1-70b-versatile", messages=[...])
-
-# Azure OpenAI
-hindsight_litellm.completion(model="azure/gpt-4", messages=[...])
-
-# AWS Bedrock
-hindsight_litellm.completion(model="bedrock/anthropic.claude-3", messages=[...])
-
-# Google Vertex AI
-hindsight_litellm.completion(model="vertex_ai/gemini-pro", messages=[...])
-```
-
-## Direct Memory APIs
-
-### Recall - Query raw memories
-
-```python
-from hindsight_litellm import configure, recall
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-memories = recall("what projects am I working on?", budget="mid")
-for m in memories:
-    print(f"- [{m.fact_type}] {m.text}")
-```
-
-### Reflect - Get synthesized context
-
-```python
-from hindsight_litellm import configure, reflect
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = reflect("what do you know about the user's preferences?")
-print(result.text)
-```
-
-### Retain - Store memories
-
-```python
-from hindsight_litellm import configure, retain
-
-configure(bank_id="my-agent", hindsight_api_url="http://localhost:8888")
-
-result = retain(
-    content="User mentioned they're working on a machine learning project",
-    context="Discussion about current projects",
-)
-```
-
-### Async APIs
-
-```python
-from hindsight_litellm import arecall, areflect, aretain
-
-# Async versions of all memory APIs
-memories = await arecall("what do you know about me?")
-context = await areflect("summarize user preferences")
-result = await aretain(content="New information to remember")
-```
-
-## Native Client Wrappers
-
-Alternative to LiteLLM callbacks for direct SDK integration.
-
-### OpenAI Wrapper
-
-```python
-from openai import OpenAI
-from hindsight_litellm import wrap_openai
-
-client = OpenAI()
-wrapped = wrap_openai(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.chat.completions.create(
-    model="gpt-4",
-    messages=[{"role": "user", "content": "What do you know about me?"}]
-)
-```
-
-### Anthropic Wrapper
-
-```python
-from anthropic import Anthropic
-from hindsight_litellm import wrap_anthropic
-
-client = Anthropic()
-wrapped = wrap_anthropic(
-    client,
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-)
-
-response = wrapped.messages.create(
-    model="claude-3-5-sonnet-20241022",
-    max_tokens=1024,
-    messages=[{"role": "user", "content": "Hello!"}]
-)
-```
-
-## Debug Mode
-
-When `verbose=True`, you can inspect exactly what memories are being injected:
-
-```python
-from hindsight_litellm import configure, enable, completion, get_last_injection_debug
-
-configure(
-    bank_id="my-agent",
-    hindsight_api_url="http://localhost:8888",
-    verbose=True,
-)
-enable()
-
-response = completion(
-    model="gpt-4o-mini",
-    messages=[{"role": "user", "content": "What's my favorite color?"}]
-)
-
-# Inspect what was injected
-debug = get_last_injection_debug()
-if debug:
-    print(f"Mode: {debug.mode}")           # "reflect" or "recall"
-    print(f"Injected: {debug.injected}")   # True/False
-    print(f"Results: {debug.results_count}")
-    print(f"Memory context:\n{debug.memory_context}")
-```
-
-## Context Manager
-
-```python
-from hindsight_litellm import hindsight_memory
-import litellm
-
-with hindsight_memory(bank_id="user-123"):
-    response = litellm.completion(model="gpt-4", messages=[...])
-# Memory integration automatically disabled after context
-```
-
-## Disabling and Cleanup
-
-```python
-from hindsight_litellm import disable, cleanup
-
-# Temporarily disable memory integration
-disable()
-
-# Clean up all resources (call when shutting down)
-cleanup()
-```
-
-## API Reference
-
-### Main Functions
-
-| Function | Description |
-|----------|-------------|
-| `configure(...)` | Configure global Hindsight settings |
-| `enable()` | Enable memory integration with LiteLLM |
-| `disable()` | Disable memory integration |
-| `is_enabled()` | Check if memory integration is enabled |
-| `cleanup()` | Clean up all resources |
-
-### Configuration Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_config()` | Get current configuration |
-| `is_configured()` | Check if Hindsight is configured |
-| `reset_config()` | Reset configuration to defaults |
-
-### Memory Functions
-
-| Function | Description |
-|----------|-------------|
-| `recall(query, ...)` | Synchronously query raw memories |
-| `arecall(query, ...)` | Asynchronously query raw memories |
-| `reflect(query, ...)` | Synchronously get synthesized memory context |
-| `areflect(query, ...)` | Asynchronously get synthesized memory context |
-| `retain(content, ...)` | Synchronously store a memory |
-| `aretain(content, ...)` | Asynchronously store a memory |
-
-### Debug Functions
-
-| Function | Description |
-|----------|-------------|
-| `get_last_injection_debug()` | Get debug info from last memory injection |
-| `clear_injection_debug()` | Clear stored debug info |
-
-### Client Wrappers
-
-| Function | Description |
-|----------|-------------|
-| `wrap_openai(client, ...)` | Wrap OpenAI client with memory |
-| `wrap_anthropic(client, ...)` | Wrap Anthropic client with memory |
-
-## Requirements
-
- Python >= 3.10
- litellm >= 1.40.0
- A running Hindsight API server
@@ -1,251 +0,0 @@
---
-sidebar_position: 8
-title: "LlamaIndex Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to LlamaIndex agents with Hindsight. Supports agent-driven tools (HindsightToolSpec) and automatic memory via the BaseMemory interface."
---
-
-# LlamaIndex
-
-Persistent long-term memory for [LlamaIndex](https://docs.llamaindex.ai/) agents via Hindsight. The `hindsight-llamaindex` package provides two complementary patterns:
-
- **`HindsightToolSpec`** — Agent-driven memory tools (retain/recall/reflect)
- **`HindsightMemory`** — Automatic memory via LlamaIndex's `BaseMemory` interface
-
-## Installation
-
-```bash
-pip install hindsight-llamaindex
-```
-
---
-
-## Automatic Memory (BaseMemory)
-
-The simplest way to add Hindsight memory to a LlamaIndex agent. Messages are automatically stored on each turn, and relevant memories are recalled and injected as context.
-
-```python
-import asyncio
-from hindsight_client import Hindsight
-from hindsight_llamaindex import HindsightMemory
-from llama_index.core.agent import ReActAgent
-from llama_index.llms.openai import OpenAI
-
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-
-    memory = HindsightMemory.from_client(
-        client=client,
-        bank_id="user-123",
-        mission="Track user preferences and project context",
-    )
-
-    agent = ReActAgent(tools=[], llm=OpenAI(model="gpt-4o"))
-    response = await agent.run("Remember that I prefer dark mode", memory=memory)
-    print(response)
-
-asyncio.run(main())
-```
-
-### How It Works
-
-| Event | What Happens |
-|-------|-------------|
-| Agent receives input | `aget(input)` recalls relevant memories from Hindsight, prepends as system message |
-| Agent produces output | `aput(message)` retains the message to Hindsight for future recall |
-| New session starts | Previous memories are available via recall; local chat buffer starts empty |
-
-### `HindsightMemory.from_client()`
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `client` | `Hindsight` | *required* | Hindsight client instance |
-| `bank_id` | `str` | *required* | Memory bank ID |
-| `mission` | `str` | `None` | Bank mission — auto-creates bank on first use |
-| `context` | `str` | `"llamaindex"` | Source label for retain operations |
-| `budget` | `str` | `"mid"` | Recall budget level |
-| `max_tokens` | `int` | `4096` | Max recall tokens |
-| `tags` | `list[str]` | `None` | Tags for retain operations |
-| `recall_tags` | `list[str]` | `None` | Tags to filter recall |
-| `recall_tags_match` | `str` | `"any"` | Tag matching mode |
-| `system_prompt` | `str` | *(built-in)* | Template for memory system message. Must contain `{memories}` |
-| `chat_history_limit` | `int` | `100` | Max messages in local buffer |
-
-Also available: `HindsightMemory.from_url(hindsight_api_url, bank_id, ...)` for creating without a pre-built client.
-
---
-
-## Agent-Driven Tools (BaseToolSpec)
-
-For explicit control, expose retain/recall/reflect as tools the agent can choose to call.
-
-### Quick Start: Tool Spec
-
-```python
-import asyncio
-from hindsight_client import Hindsight
-from hindsight_llamaindex import HindsightToolSpec
-from llama_index.llms.openai import OpenAI
-from llama_index.core.agent import ReActAgent
-
-async def main():
-    client = Hindsight(base_url="http://localhost:8888")
-
-    spec = HindsightToolSpec(
-        client=client,
-        bank_id="user-123",
-        mission="Track user preferences",
-    )
-    tools = spec.to_tool_list()
-
-    agent = ReActAgent(tools=tools, llm=OpenAI(model="gpt-4o"))
-    response = await agent.run("Remember that I prefer dark mode")
-    print(response)
-
-asyncio.run(main())
-```
-
-### Quick Start: Factory Function
-
-```python
-from hindsight_llamaindex import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    mission="Track user preferences",
-)
-```
-
-### Selecting Tools
-
-```python
-# Via to_tool_list()
-tools = spec.to_tool_list(spec_functions=["recall_memory", "reflect_on_memory"])
-
-# Via factory flags
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,
-)
-```
-
-### Configuration
-
-Set defaults via `configure()`, override per-call:
-
-```python
-from hindsight_llamaindex import configure
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",  # or set HINDSIGHT_API_KEY env var
-    budget="mid",
-    tags=["source:llamaindex"],
-    context="my-app",
-    mission="Track user preferences",
-)
-
-# Now create tools without passing client/url
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-### `HindsightToolSpec()`
-
-| Parameter | Type | Default | Description |
-|-----------|------|---------|-------------|
-| `bank_id` | `str` | *required* | Hindsight memory bank to operate on |
-| `client` | `Hindsight` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `str` | `None` | API URL (used if no client provided) |
-| `api_key` | `str` | `None` | API key (used if no client provided) |
-| `budget` | `str` | `None` → `"mid"` | Recall/reflect budget: `low`, `mid`, `high` |
-| `max_tokens` | `int` | `None` → `4096` | Max tokens for recall results |
-| `tags` | `list[str]` | `None` | Tags applied when storing memories |
-| `recall_tags` | `list[str]` | `None` | Tags to filter recall results |
-| `recall_tags_match` | `str` | `None` → `"any"` | Tag matching: `any`, `all`, `any_strict`, `all_strict` |
-| `retain_metadata` | `dict[str, str]` | `None` | Default metadata for retain operations |
-| `retain_document_id` | `str` | `None` | Document ID for retain. Auto-generates `{session}-{timestamp}` if not set |
-| `retain_context` | `str` | `"llamaindex"` | Source label for retain operations |
-| `recall_types` | `list[str]` | `None` | Fact types: `world`, `experience`, `opinion`, `observation` |
-| `recall_include_entities` | `bool` | `False` | Include entity info in recall results |
-| `reflect_context` | `str` | `None` | Additional context for reflect |
-| `reflect_max_tokens` | `int` | `None` | Max tokens for reflect (defaults to `max_tokens`) |
-| `reflect_response_schema` | `dict` | `None` | JSON schema to constrain reflect output |
-| `reflect_tags` | `list[str]` | `None` | Tags for reflect (defaults to `recall_tags`) |
-| `reflect_tags_match` | `str` | `None` | Tag matching for reflect (defaults to `recall_tags_match`) |
-| `mission` | `str` | `None` | Bank mission — auto-creates bank on first use |
-
---
-
-## Production Patterns
-
-### Bank Mission
-
-Set a mission to give the memory engine context for fact extraction:
-
-```python
-# Tools
-spec = HindsightToolSpec(
-    client=client,
-    bank_id="user-123",
-    mission="Track user coding preferences, project context, and technical decisions",
-)
-
-# Memory
-memory = HindsightMemory.from_client(
-    client=client,
-    bank_id="user-123",
-    mission="Track user coding preferences, project context, and technical decisions",
-)
-```
-
-The bank is created automatically on first use. If it already exists, creation is silently skipped.
-
-### Memory Scoping with Tags
-
-```python
-spec = HindsightToolSpec(
-    client=client,
-    bank_id="user-123",
-    tags=["source:chat", "session:abc"],        # applied to all retains
-    recall_tags=["source:chat"],                 # filter recalls to chat memories
-    recall_tags_match="any",
-)
-```
-
-### Error Handling
-
-Both patterns handle errors gracefully — operations are logged and return friendly messages instead of raising exceptions. Agents continue functioning even if memory is unavailable.
-
-### Combining Tools + Memory
-
-Use both patterns together for maximum flexibility:
-
-```python
-from hindsight_llamaindex import create_hindsight_tools, HindsightMemory
-
-# Automatic memory for context enrichment
-memory = HindsightMemory.from_client(client=client, bank_id="user-123")
-
-# Explicit tools for agent-driven reflect
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=False,   # memory handles retain automatically
-    include_recall=False,   # memory handles recall automatically
-    include_reflect=True,   # agent can still explicitly reflect
-)
-
-agent = ReActAgent(tools=tools, llm=llm)
-
-# Pass memory to run()
-response = await agent.run("What should I prioritize?", memory=memory)
-```
-
-## Requirements
-
- Python 3.10+
- `llama-index-core >= 0.11.0`
- `hindsight-client >= 0.4.0`
@@ -1,176 +0,0 @@
---
-sidebar_position: 2
-title: "Hindsight Local MCP Server | Persistent Memory for Claude"
-description: "Run Hindsight as a local MCP server with embedded PostgreSQL — no external setup required. Ideal for Claude Code and Claude Desktop for long-term memory across conversations."
---
-
-# Local MCP Server
-
-Hindsight provides a local MCP server that runs entirely on your machine with an embedded PostgreSQL database. No external server or database setup required.
-
-This is ideal for:
- **Personal use with Claude Code / Claude Desktop** — Give Claude long-term memory across conversations
- **Development and testing** — Quick setup without infrastructure
- **Privacy-focused setups** — All data stays on your machine
-
-## How It Works
-
-Running `hindsight-local-mcp` starts the full Hindsight API on `localhost:8888` with an embedded PostgreSQL database (pg0). You then connect your MCP client to it over HTTP.
-
- Starts an embedded PostgreSQL (pg0) automatically
- Runs database migrations on startup
- Exposes the full MCP endpoint at `http://localhost:8888/mcp/`
- Data persists in `~/.pg0/hindsight-mcp/` across restarts
-
-## Setup
-
-### 1. Start the server
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... uvx --from hindsight-api hindsight-local-mcp
-```
-
-Or with Ollama (no API key needed):
-
-```bash
-HINDSIGHT_API_LLM_PROVIDER=ollama HINDSIGHT_API_LLM_MODEL=llama3.2 uvx --from hindsight-api hindsight-local-mcp
-```
-
-### 2. Configure your MCP client
-
-**Claude Code:**
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/
-```
-
-**Other MCP clients** — add an HTTP transport entry pointing to `http://localhost:8888/mcp/`.
-
-## Bank Modes
-
-The local server supports the same two modes as the hosted API:
-
-### Multi-bank mode (default)
-
-Use `http://localhost:8888/mcp/` — exposes all tools including bank management. Bank is selected per-request via the `bank_id` tool parameter or the `X-Bank-Id` header.
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/
-```
-
-### Single-bank mode
-
-Use `http://localhost:8888/mcp/<bank-id>/` — pins all tools to one bank, no `bank_id` parameter needed. This replaces the old `HINDSIGHT_API_MCP_LOCAL_BANK_ID` env var.
-
-```bash
-claude mcp add --transport http hindsight http://localhost:8888/mcp/my-bank/
-```
-
-## Available Tools
-
-The local server exposes the full tool set (29 tools in multi-bank mode, 26 in single-bank mode):
-
-**Core Memory**
-
-| Tool | Description |
-|------|-------------|
-| `retain` | Store information to long-term memory with optional tags, metadata, and document association |
-| `recall` | Search memories with natural language, configurable budget, type filters, and tag filters |
-| `reflect` | Synthesize memories into a reasoned answer with optional structured output |
-
-**Mental Models**
-
-| Tool | Description |
-|------|-------------|
-| `list_mental_models` | List pinned reflections for a bank |
-| `get_mental_model` | Get a specific mental model |
-| `create_mental_model` | Create a new mental model with optional auto-refresh trigger |
-| `update_mental_model` | Update a mental model's metadata |
-| `delete_mental_model` | Delete a mental model |
-| `refresh_mental_model` | Regenerate a mental model's content |
-
-**Directives**
-
-| Tool | Description |
-|------|-------------|
-| `list_directives` | List directives that guide memory processing |
-| `create_directive` | Create a new directive |
-| `delete_directive` | Delete a directive |
-
-**Memory Browsing**
-
-| Tool | Description |
-|------|-------------|
-| `list_memories` | Browse memories with filtering and pagination |
-| `get_memory` | Get a specific memory by ID |
-| `delete_memory` | Delete a specific memory |
-
-**Documents**
-
-| Tool | Description |
-|------|-------------|
-| `list_documents` | List ingested documents |
-| `get_document` | Get a specific document |
-| `delete_document` | Delete a document and its linked memories |
-
-**Operations**
-
-| Tool | Description |
-|------|-------------|
-| `list_operations` | List async operations with status filtering |
-| `get_operation` | Check operation status and progress |
-| `cancel_operation` | Cancel a pending or running operation |
-
-**Tags & Bank Management**
-
-| Tool | Description |
-|------|-------------|
-| `list_tags` | List unique tags used in a bank |
-| `get_bank` | Get bank profile (name, mission, disposition) |
-| `get_bank_stats` | Get bank statistics (multi-bank only) |
-| `update_bank` | Update bank name or mission |
-| `delete_bank` | Delete an entire bank and all its data |
-| `clear_memories` | Clear memories without deleting the bank |
-| `list_banks` | List all memory banks (multi-bank only) |
-| `create_bank` | Create or configure a memory bank (multi-bank only) |
-
-For detailed parameter documentation, see the [MCP Server reference](../../developer/mcp-server.md#available-tools).
-
-## Environment Variables
-
-All standard [Hindsight configuration variables](../../developer/configuration.md) are supported. Key ones for local use:
-
-| Variable | Required | Default | Description |
-|----------|----------|---------|-------------|
-| `HINDSIGHT_API_LLM_API_KEY` | Yes* | — | API key for your LLM provider |
-| `HINDSIGHT_API_LLM_PROVIDER` | No | `openai` | LLM provider (`openai`, `anthropic`, `ollama`, etc.) |
-| `HINDSIGHT_API_LLM_MODEL` | No | `gpt-4o-mini` | Model name |
-| `HINDSIGHT_API_DATABASE_URL` | No | `pg0://hindsight-mcp` | Override the database URL |
-| `HINDSIGHT_API_PORT` | No | `8888` | Port to listen on |
-| `HINDSIGHT_API_LOG_LEVEL` | No | `info` | Log level |
-
-*Not required when using a local provider like Ollama.
-
-## Troubleshooting
-
-### Slow first startup
-
-The first startup downloads the local embedding model (~100MB) and initializes the database. Subsequent starts are faster.
-
-### Port already in use
-
-Set a different port:
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... HINDSIGHT_API_PORT=9000 uvx --from hindsight-api hindsight-local-mcp
-```
-
-Then update your MCP client URL to `http://localhost:9000/mcp/`.
-
-### Checking logs
-
-Set `HINDSIGHT_API_LOG_LEVEL=debug` for verbose output:
-
-```bash
-HINDSIGHT_API_LLM_API_KEY=sk-... HINDSIGHT_API_LOG_LEVEL=debug uvx --from hindsight-api hindsight-local-mcp
-```
@@ -1,250 +0,0 @@
---
-sidebar_position: 5
-title: "NemoClaw Persistent Memory with Hindsight | Integration Guide"
-description: "Add persistent memory to NemoClaw sandboxed agents with Hindsight. One command adds automated memory extraction and auto-recall to any NemoClaw sandbox — no code changes required."
---
-
-# NemoClaw
-
-Persistent memory for [NemoClaw](https://nemoclaw.ai) sandboxed agents using [Hindsight](https://hindsight.vectorize.io).
-
-NemoClaw runs [OpenClaw](https://openclaw.ai) inside an OpenShell sandbox with controlled filesystem, process, and network egress policies. The `hindsight-nemoclaw` package automates adding Hindsight memory to a sandbox in one command — no code changes required.
-
-[View Changelog →](../../changelog/integrations/nemoclaw.md)
-
-## Quick Start
-
-```bash
-npx @vectorize-io/hindsight-nemoclaw setup \
-  --sandbox my-assistant \
-  --api-url https://api.hindsight.vectorize.io \
-  --api-token <your-api-key> \
-  --bank-prefix my-sandbox
-```
-
-Get an API key at [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup).
-
-You'll see output like:
-
-```
-[0] Preflight checks...
-  ✓ openshell found
-  ✓ openclaw found
-
-[1] Installing @vectorize-io/hindsight-openclaw plugin...
-  ✓ Plugin installed
-
-[2] Configuring plugin in ~/.openclaw/openclaw.json...
-  ✓ Plugin config written (bank: my-sandbox-openclaw)
-
-[3] Applying Hindsight network policy to sandbox "my-assistant"...
-  ✓ Policy version 2 submitted
-  ✓ Policy version 2 loaded (active version: 2)
-
-[4] Restarting OpenClaw gateway...
-  ✓ Gateway restarted
-
-✓ Setup complete!
-```
-
-## How It Works
-
-### The sandbox problem
-
-OpenShell enforces strict network egress — every outbound endpoint must be explicitly permitted in the sandbox policy. By default, the Hindsight API (`api.hindsight.vectorize.io`) is not in that list.
-
-The `hindsight-openclaw` plugin supports **external API mode**, where it skips the local daemon entirely and makes direct HTTPS calls to Hindsight Cloud. This is the natural fit for sandboxed environments: the plugin becomes a thin HTTP client, and the only sandbox change needed is one egress rule.
-
-### What the setup command does
-
-1. **Preflight** — verifies `openshell` and `openclaw` are installed
-2. **Install plugin** — runs `openclaw plugins install @vectorize-io/hindsight-openclaw`
-3. **Configure plugin** — writes external API mode config to `~/.openclaw/openclaw.json`
-4. **Apply policy** — reads the current sandbox policy, merges the Hindsight egress block, and re-applies via `openshell policy set`
-5. **Restart gateway** — runs `openclaw gateway restart`
-
-### Memory flow
-
-Once set up, the `hindsight-openclaw` plugin hooks into the OpenClaw gateway lifecycle:
-
- **`before_agent_start`** — recalls relevant memories from past sessions and injects them into context
- **`agent_end`** — retains the conversation to the Hindsight memory bank
-
-The sandbox doesn't interfere with either step — it sees the Hindsight calls as normal HTTPS egress to a permitted endpoint.
-
-## CLI Reference
-
-```
-hindsight-nemoclaw setup [options]
-
-Options:
-  --sandbox <name>       NemoClaw sandbox name (required)
-  --api-url <url>        Hindsight API URL (required)
-  --api-token <token>    Hindsight API token (required)
-  --bank-prefix <prefix> Memory bank prefix (default: "nemoclaw")
-  --skip-policy          Skip sandbox network policy update
-  --skip-plugin-install  Skip openclaw plugin installation
-  --dry-run              Preview changes without applying
-  --help                 Show help
-```
-
-Use `--dry-run` to preview all changes before applying anything. Use `--skip-policy` if you manage sandbox policies manually.
-
-## Manual Setup
-
-If you prefer to apply the steps yourself instead of using the CLI:
-
-### 1. Install the plugin
-
-```bash
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### 2. Configure `~/.openclaw/openclaw.json`
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "hindsightApiUrl": "https://api.hindsight.vectorize.io",
-          "hindsightApiToken": "<your-api-key>",
-          "llmProvider": "claude-code",
-          "dynamicBankId": false,
-          "bankIdPrefix": "my-sandbox"
-        }
-      }
-    }
-  }
-}
-```
-
-`llmProvider: "claude-code"` uses the Claude Code process already present in the sandbox — no additional API key needed.
-
-### 3. Add the Hindsight network policy
-
-`openshell policy set` replaces the entire policy document. Export your current policy first, add the Hindsight block, then re-apply:
-
-```yaml
-network_policies:
-  hindsight:
-    name: hindsight
-    endpoints:
-      - host: api.hindsight.vectorize.io
-        port: 443
-        protocol: rest
-        tls: terminate
-        enforcement: enforce
-        rules:
-          - allow:
-              method: GET
-              path: /**
-          - allow:
-              method: POST
-              path: /**
-          - allow:
-              method: PUT
-              path: /**
-    binaries:
-      - path: /usr/local/bin/openclaw
-```
-
-```bash
-openshell policy set my-sandbox --policy /path/to/full-policy.yaml --wait
-openclaw gateway restart
-```
-
-## Configuration Options
-
-| Option | Type | Default | Description |
-|---|---|---|---|
-| `hindsightApiUrl` | string | — | Hindsight API base URL |
-| `hindsightApiToken` | string | — | API token for authentication |
-| `llmProvider` | string | auto-detect | LLM provider for memory extraction |
-| `dynamicBankId` | boolean | `false` | Isolate memory per user (`true`) or share across sessions (`false`) |
-| `bankIdPrefix` | string | `"nemoclaw"` | Prefix for the memory bank name |
-
-### Bank naming
-
-When `dynamicBankId: false`, all sessions write to a single bank named `{bankIdPrefix}-openclaw`. When `dynamicBankId: true`, each user gets an isolated bank — useful for multi-tenant deployments.
-
-## Verifying It Works
-
-After setup, check the gateway logs:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-```
-
-On startup you should see:
-
-```
-[Hindsight] Plugin loaded successfully
-[Hindsight] ✓ Using external API: https://api.hindsight.vectorize.io
-[Hindsight] External API health: {"status":"healthy","database":"connected"}
-[Hindsight] Default bank: my-sandbox-openclaw
-[Hindsight] ✓ Ready (external API mode)
-```
-
-After a conversation:
-
-```
-[Hindsight] before_agent_start - bank: my-sandbox-openclaw, channel: undefined/webchat
-[Hindsight Hook] agent_end triggered - bank: my-sandbox-openclaw
-[Hindsight] Retained 6 messages to bank my-sandbox-openclaw for session agent:main:...
-```
-
-## Pitfalls
-
-### Policy replacement is full-document
-
-`openshell policy set` replaces the entire policy document. The `hindsight-nemoclaw setup` command handles this automatically. If you're applying manually, export the current policy first so existing rules aren't lost.
-
-### LaunchAgent can't follow symlinks on macOS
-
-On macOS, the OpenClaw gateway runs as a LaunchAgent under a restricted security context. `openclaw plugins install --link` creates a symlink the LaunchAgent can't follow — the setup command installs as a copy instead. If you see `EPERM: operation not permitted, scandir` in gateway logs, this is the cause.
-
-### Memory retention is asynchronous
-
-Fact extraction and entity resolution happen in the background after `retain`. If you open a new session immediately after closing one, the most recent memories may not be indexed yet — typically a few seconds.
-
-### Binary-scoped egress
-
-The `binaries` field in the network policy restricts the egress rule to a specific executable path. If OpenClaw updates and the binary path changes, the rule silently stops working. Check your binary path after upgrades.
-
-## Troubleshooting
-
-### Plugin not loading
-
-```bash
-openclaw plugins list | grep hindsight
-# Should show: ✓ enabled │ Hindsight Memory │ ...
-
-# Reinstall
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### Egress blocked
-
-If calls to `api.hindsight.vectorize.io` are being blocked, check the active sandbox policy:
-
-```bash
-openshell sandbox get my-assistant
-```
-
-Verify the `hindsight` block is present and the `binaries` path matches your OpenClaw binary:
-
-```bash
-which openclaw
-```
-
-### External API not connecting
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# If you see daemon startup messages instead of "Using external API",
-# the plugin config isn't being read — check ~/.openclaw/openclaw.json
-```
@@ -1,374 +0,0 @@
---
-sidebar_position: 4
-title: "OpenClaw Persistent Memory with Hindsight | Plugin Integration"
-description: "Add persistent, automated memory to your OpenClaw agent with Hindsight. Local-first, open source — one plugin install replaces built-in memory with structured knowledge extraction and auto-recall."
---
-
-# OpenClaw
-
-Local, long term memory for [OpenClaw](https://openclaw.ai) agents using [Hindsight](https://vectorize.io/hindsight).
-
-This plugin integrates [hindsight-embed](https://vectorize.io/hindsight/cli), a standalone daemon that bundles Hindsight's memory engine (API + PostgreSQL) into a single command. Everything runs locally on your machine, reuses the LLM you're already paying for, and costs nothing extra.
-
-[View Changelog →](../../changelog/integrations/openclaw.md)
-
-## Quick Start
-
-**Step 1: Set up LLM for memory extraction**
-
-Choose one provider and set its API key:
-
-```bash
-# Option A: OpenAI
-export OPENAI_API_KEY="sk-your-key"
-
-# Option B: Anthropic
-export ANTHROPIC_API_KEY="your-key"
-
-# Option C: Gemini
-export GEMINI_API_KEY="your-key"
-
-# Option D: Groq
-export GROQ_API_KEY="your-key"
-
-# Option E: Claude Code (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=claude-code
-
-# Option F: OpenAI Codex (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=openai-codex
-```
-
-**Step 2: Install the plugin**
-
-```bash
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-**Step 3: Start OpenClaw**
-
-```bash
-openclaw gateway
-```
-
-The plugin will automatically:
- Start a local Hindsight daemon (port 9077)
- Capture conversations after each turn
- Inject relevant memories before agent responses
-
-**Important:** The LLM you configure above is **only for memory extraction** (background processing). Your main OpenClaw agent can use any model you configure separately.
-
-## How It Works
-
-**Auto-Capture:** Every conversation is automatically stored after each turn. Facts, entities, and relationships are extracted in the background.
-
-**Auto-Recall:** Before each agent response, relevant memories are automatically injected into the context (up to 1024 tokens). The agent uses past context without needing to call tools.
-
-**Feedback Loop Prevention:** The plugin automatically strips injected memory tags (`<hindsight_memories>`) before storing conversations. This prevents recalled memories from being re-extracted as new facts, which would cause exponential memory growth and duplicate entries.
-
-Traditional memory systems give agents a `search_memory` tool - but models don't use it consistently. Auto-recall solves this by injecting memories automatically before every turn.
-
-## Configuration
-
-### Plugin Settings
-
-Optional settings in `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "apiPort": 9077,
-          "daemonIdleTimeout": 0,
-          "embedVersion": "latest"
-        }
-      }
-    }
-  }
-}
-```
-
-**Options:**
- `apiPort` - Port for the openclaw profile daemon (default: `9077`)
- `daemonIdleTimeout` - Seconds before daemon shuts down from inactivity (default: `0` = never)
- `embedVersion` - hindsight-embed version (default: `"latest"`)
- `bankMission` - Agent identity/purpose stored on the memory bank. Helps the memory engine understand context for better fact extraction during retain. Set once per bank on first use — not a recall prompt.
- `dynamicBankId` - Enable per-context memory banks (default: `true`)
- `bankIdPrefix` - Optional prefix for bank IDs (e.g. `"prod"` → `"prod-slack-C123"`)
- `dynamicBankGranularity` - Fields used to derive bank ID: `agent`, `channel`, `user`, `provider` (default: `["agent", "channel", "user"]`)
- `excludeProviders` - Message providers to skip for recall/retain (e.g. `["slack"]`, `["telegram"]`, `["discord"]`)
- `autoRecall` - Auto-inject memories before each turn (default: `true`). Set to `false` when the agent has its own recall tool.
- `autoRetain` - Auto-retain conversations after each turn (default: `true`)
- `retainRoles` - Which message roles to retain (default: `["user", "assistant"]`). Options: `user`, `assistant`, `system`, `tool`
- `recallBudget` - Recall effort: `"low"`, `"mid"`, or `"high"` (default: `"mid"`). Higher budgets use more retrieval strategies for better results.
- `recallMaxTokens` - Max tokens for recall response (default: `1024`). Controls how much memory context is injected per turn.
- `recallTopK` - Max number of memories to inject per turn (default: unlimited).
- `recallTypes` - Memory types to recall (default: `["world", "experience"]`). Options: `world`, `experience`, `observation`.
- `recallContextTurns` - Number of prior user turns to include in the recall query (default: `1`).
- `recallMaxQueryChars` - Max characters for the composed recall query (default: `800`).
- `recallPromptPreamble` - Custom preamble text placed above recalled memories. Overrides the built-in guidance text.
- `recallInjectionPosition` - Where to inject recalled memories: `"prepend"` (default), `"append"`, or `"user"`. Use `"append"` to preserve prompt caching with large static system prompts. Use `"user"` to inject before the user message instead of in the system prompt.
- `recallRoles` - Which message roles to include when composing the contextual recall query (default: `["user", "assistant"]`).
- `retainEveryNTurns` - Retain every Nth turn (default: `1` = every turn). Values > 1 enable chunked retention.
- `retainOverlapTurns` - Extra prior turns included when chunked retention fires (default: `0`).
- `debug` - Enable debug logging (default: `false`).
-
-### Memory Isolation
-
-The plugin creates separate memory banks based on conversation context. By default, banks are derived from the `agent`, `channel`, and `user` fields — so each unique combination gets its own isolated memory store.
-
-You can customize which fields are used for bank segmentation with `dynamicBankGranularity`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "dynamicBankGranularity": ["provider", "user"]
-        }
-      }
-    }
-  }
-}
-```
-
-In this example, memories are isolated per provider + user, meaning the same user shares memories across all channels within a provider.
-
-Available isolation fields:
- `agent` - The agent/bot identity
- `channel` - The channel or conversation ID
- `user` - The user interacting with the agent
- `provider` - The message provider (e.g. Slack, Discord)
-
-Use `bankIdPrefix` to namespace bank IDs across environments (e.g. `"prod"`, `"staging"`). Set `dynamicBankId` to `false` to use a single shared bank for all conversations.
-
-### Retention Controls
-
-By default, the plugin retains `user` and `assistant` messages after each turn. You can customize this behavior:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "autoRetain": true,
-          "retainRoles": ["user", "assistant", "system"]
-        }
-      }
-    }
-  }
-}
-```
-
- `autoRetain` - Set to `false` to disable automatic retention entirely (useful if you handle retention yourself)
- `retainRoles` - Controls which message roles are included in the retained transcript. Only messages from the last user message onward are retained each turn, preventing duplicate storage.
-
-### LLM Configuration
-
-The plugin auto-detects your LLM provider from these environment variables:
-
-| Provider | Env Var | Notes |
-|----------|---------|-------|
-| OpenAI | `OPENAI_API_KEY` | |
-| Anthropic | `ANTHROPIC_API_KEY` | |
-| Gemini | `GEMINI_API_KEY` | |
-| Groq | `GROQ_API_KEY` | |
-| Claude Code | `HINDSIGHT_API_LLM_PROVIDER=claude-code` | No API key needed |
-| OpenAI Codex | `HINDSIGHT_API_LLM_PROVIDER=openai-codex` | No API key needed |
-
-The model is selected automatically by the Hindsight API. To override, set `HINDSIGHT_API_LLM_MODEL`.
-
-**Override with explicit config:**
-
-```bash
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_API_KEY=sk-your-key
-
-# Optional: custom base URL (OpenRouter, Azure, vLLM, etc.)
-export HINDSIGHT_API_LLM_BASE_URL=https://openrouter.ai/api/v1
-```
-
-**Example: Free OpenRouter model**
-
-```bash
-export HINDSIGHT_API_LLM_PROVIDER=openai
-export HINDSIGHT_API_LLM_MODEL=xiaomi/mimo-v2-flash  # FREE!
-export HINDSIGHT_API_LLM_API_KEY=sk-or-v1-your-openrouter-key
-export HINDSIGHT_API_LLM_BASE_URL=https://openrouter.ai/api/v1
-```
-
-### External API (Advanced)
-
-Connect to a remote Hindsight API server instead of running a local daemon. This is useful for:
-
- **Shared memory** across multiple OpenClaw instances
- **Production deployments** with centralized memory storage
- **Team environments** where agents share knowledge
-
-#### Plugin Configuration
-
-Configure in `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "plugins": {
-    "entries": {
-      "hindsight-openclaw": {
-        "enabled": true,
-        "config": {
-          "hindsightApiUrl": "https://your-hindsight-server.com",
-          "hindsightApiToken": "your-api-token"
-        }
-      }
-    }
-  }
-}
-```
-
-**Options:**
- `hindsightApiUrl` - Full URL to external Hindsight API (e.g., `https://mcp.hindsight.example.com`)
- `hindsightApiToken` - API token for authentication (optional, only if API requires auth)
-
-#### Environment Variables (Alternative)
-
-You can also configure via environment variables:
-
-```bash
-export HINDSIGHT_EMBED_API_URL=https://your-hindsight-server.com
-export HINDSIGHT_EMBED_API_TOKEN=your-api-token  # Optional
-
-openclaw gateway
-```
-
-**Note:** Plugin config takes precedence over environment variables.
-
-#### Behavior
-
-When external API mode is enabled:
- **No local daemon** is started (no hindsight-embed process)
- **Health check** runs on startup to verify API connectivity
- **All memory operations** (retain, recall, reflect) go to the external API
- **Faster startup** since no local PostgreSQL or embedding models are needed
-
-#### Verification
-
-Check OpenClaw logs for external API mode:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# Should see on startup:
-# [Hindsight] External API mode enabled: https://your-hindsight-server.com
-# [Hindsight] External API health check passed
-```
-
-If you see daemon startup messages instead, verify your configuration is correct.
-
-## Inspecting Memories
-
-### Check Configuration
-
-View the daemon config that was written by the plugin:
-
-```bash
-cat ~/.hindsight/profiles/openclaw.env
-```
-
-This shows the LLM provider, model, port, and other settings the daemon is using.
-
-### Check Daemon Status
-
-```bash
-# Check if daemon is running
-uvx hindsight-embed@latest -p openclaw daemon status
-
-# View daemon logs
-tail -f ~/.hindsight/profiles/openclaw.log
-```
-
-### Query Memories
-
-```bash
-# Search memories
-uvx hindsight-embed@latest -p openclaw memory recall openclaw "user preferences"
-
-# View recent memories
-uvx hindsight-embed@latest -p openclaw memory list openclaw --limit 10
-
-# Open web UI (uses openclaw profile's daemon)
-uvx hindsight-embed@latest -p openclaw ui
-```
-
-## Troubleshooting
-
-### Plugin not loading
-
-```bash
-openclaw plugins list | grep hindsight
-# Should show: ✓ enabled │ Hindsight Memory │ ...
-
-# Reinstall if needed
-openclaw plugins install @vectorize-io/hindsight-openclaw
-```
-
-### Daemon not starting
-
-```bash
-# Check daemon status (note: -p openclaw uses the openclaw profile)
-uvx hindsight-embed@latest -p openclaw daemon status
-
-# View logs for errors
-tail -f ~/.hindsight/profiles/openclaw.log
-
-# Check configuration
-cat ~/.hindsight/profiles/openclaw.env
-
-# List all profiles
-uvx hindsight-embed@latest profile list
-```
-
-### No API key error
-
-Make sure you've set one of the provider API keys (or use a provider that doesn't require one):
-
-```bash
-# Option 1: OpenAI
-export OPENAI_API_KEY="sk-your-key"
-
-# Option 2: Anthropic
-export ANTHROPIC_API_KEY="your-key"
-
-# Option 3: Claude Code (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=claude-code
-
-# Option 4: OpenAI Codex (no API key needed)
-export HINDSIGHT_API_LLM_PROVIDER=openai-codex
-
-# Verify it's set
-echo $OPENAI_API_KEY
-# or
-echo $HINDSIGHT_API_LLM_PROVIDER
-```
-
-### Verify it's working
-
-Check gateway logs for memory operations:
-
-```bash
-tail -f /tmp/openclaw/openclaw-*.log | grep Hindsight
-
-# Should see on startup:
-# [Hindsight] ✓ Using provider: openai, model: gpt-4o-mini
-# or
-# [Hindsight] ✓ Using provider: claude-code, model: claude-sonnet-4-20250514
-
-# Should see after conversations:
-# [Hindsight] Retained X messages for session ...
-# [Hindsight] Auto-recall: Injecting X memories
-```
@@ -1,188 +0,0 @@
---
-sidebar_position: 6
-title: "Pydantic AI Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Pydantic AI agents with Hindsight. Async-native retain, recall, and reflect tools — persistent memory across all agent runs with no thread-pool hacks."
---
-
-# Pydantic AI
-
-Persistent memory tools for [Pydantic AI](https://ai.pydantic.dev/) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — all async-native with no thread-pool hacks.
-
-[View Changelog →](../../changelog/integrations/pydantic-ai.md)
-
-## Features
-
- **Async-Native Tools** — Uses Pydantic AI's async tool interface directly (`aretain`, `arecall`, `areflect`)
- **Memory Instructions** — Auto-inject relevant memories into every agent run via `instructions=[...]`
- **Three Memory Tools** — Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Simple Configuration** — Configure once globally, or pass a client directly
- **Lightweight** — Depends on `pydantic-ai-slim` to avoid pulling in all model providers
-
-## Installation
-
-```bash
-pip install hindsight-pydantic-ai
-```
-
-## Quick Start
-
-```python
-from hindsight_client import Hindsight
-from hindsight_pydantic_ai import create_hindsight_tools, memory_instructions
-from pydantic_ai import Agent
-
-client = Hindsight(base_url="http://localhost:8888")
-
-agent = Agent(
-    "openai:gpt-4o",
-    tools=create_hindsight_tools(client=client, bank_id="user-123"),
-    instructions=[memory_instructions(client=client, bank_id="user-123")],
-)
-
-result = await agent.run("What do you remember about my preferences?")
-print(result.output)
-```
-
-The agent now has three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-The `memory_instructions` callable automatically recalls relevant memories and injects them into the system prompt on every run.
-
-## Tools Only (No Auto-Injection)
-
-If you want the agent to decide when to use memory rather than always injecting context:
-
-```python
-agent = Agent(
-    "openai:gpt-4o",
-    tools=create_hindsight_tools(client=client, bank_id="user-123"),
-)
-```
-
-## Instructions Only (No Tools)
-
-If you just want memories auto-injected without giving the agent explicit memory tools:
-
-```python
-agent = Agent(
-    "openai:gpt-4o",
-    instructions=[memory_instructions(client=client, bank_id="user-123")],
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    client=client,
-    bank_id="user-123",
-    include_retain=True,
-    include_recall=True,
-    include_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing a client to every call, configure once:
-
-```python
-from hindsight_pydantic_ai import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing client — uses global config
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Per-Tool Overrides
-
-Constructor arguments override global configuration:
-
-```python
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    budget="high",             # Override global budget
-    max_tokens=8192,           # Override global max_tokens
-    tags=["session:abc"],      # Override global tags
-)
-```
-
-## Memory Instructions Options
-
-Customize what memories get injected and how:
-
-```python
-instructions_fn = memory_instructions(
-    client=client,
-    bank_id="user-123",
-    query="relevant context about the user",  # What to search for
-    budget="low",                              # Keep it fast
-    max_results=5,                             # Limit injected memories
-    max_tokens=4096,                           # Max recall tokens
-    prefix="Relevant memories:\n",             # Text before the memory list
-    tags=["scope:global"],                     # Filter by tags
-    tags_match="any",                          # Tag match mode
-)
-```
-
-## API Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `include_retain` | `True` | Include the retain (store) tool |
-| `include_recall` | `True` | Include the recall (search) tool |
-| `include_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
@@ -1,325 +0,0 @@
---
-sidebar_position: 3
-title: "Hindsight Agent Memory Skill | AI Coding Assistant Integration"
-description: "Give AI coding assistants like Claude Code and Codex persistent memory across sessions with Hindsight's Agent Skill — a reusable prompt template for long-term context retention."
---
-
-# Skills
-
-Hindsight provides an Agent Skill that gives AI coding assistants persistent memory across sessions. Skills are reusable prompt templates that agents can load when needed to gain specialized capabilities.
-
-## Supported Platforms
-
-| Platform | Skills Directory |
-|----------|-----------------|
-| [Claude Code](https://docs.anthropic.com/en/docs/claude-code) | `~/.claude/skills/` |
-| [OpenCode](https://github.com/opencode-ai/opencode) | `~/.opencode/skills/` |
-| [Codex CLI](https://github.com/openai/codex) | `~/.codex/skills/` |
-
-## Deployment Modes
-
-The skill supports two deployment modes:
-
-| Mode | Best For | Data Location |
-|------|----------|---------------|
-| **Local** | Individual developers | Your machine (`~/.pg0/`) |
-| **Cloud** | Teams sharing knowledge | Hindsight Cloud |
-
-## Quick Install
-
-### Option 1: Interactive Installer (Recommended)
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash
-```
-
-The installer will:
-1. Prompt you to select your AI coding assistant
-2. Select deployment mode (local or cloud)
-3. Configure the appropriate settings
-4. Install the skill to the appropriate directory
-
-### Install for a Specific Platform
-
-```bash
-# Claude Code (interactive mode selection)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude
-
-# OpenCode
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app opencode
-
-# Codex CLI
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app codex
-```
-
-### Install with Cloud Mode
-
-```bash
-# Direct cloud setup (skips interactive prompts for mode)
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --app claude --mode cloud
-```
-
-### Option 2: Using add-skill
-
-If you use [add-skill](https://add-skill.org/) to manage your agent skills:
-
-```bash
-# For local mode (individual developers)
-npx add-skill vectorize-io/hindsight --skill hindsight-local
-
-# For Hindsight Cloud (teams)
-npx add-skill vectorize-io/hindsight --skill hindsight-cloud
-
-# For self-hosted Hindsight servers
-npx add-skill vectorize-io/hindsight --skill hindsight-self-hosted
-```
-
-On first use, the AI will guide you through the remaining setup:
- **Local**: Run `uvx hindsight-embed configure` to set up your LLM provider
- **Cloud**: Provide your API key and bank ID
- **Self-hosted**: Provide your server URL, API key, and bank ID
-
-## What the Skill Provides
-
-Once installed, your AI assistant gains the ability to:
-
- **Retain** - Store user preferences, learnings, and procedure outcomes
- **Recall** - Search for relevant context before starting tasks
- **Reflect** - Synthesize memories into contextual answers
-
-The skill uses the `hindsight-embed` CLI which runs a lightweight local daemon with an embedded database.
-
-## How Skills Work
-
-Skills are **model-invoked**, meaning the AI assistant automatically decides when to use them based on the context of your conversation. You don't need to explicitly trigger the skill.
-
-The assistant will:
- **Store** when you share preferences, when tasks succeed/fail, or when learnings emerge
- **Recall** before starting non-trivial tasks to get relevant context
-
-### What Gets Stored
-
-The skill is optimized to store:
-
-| Category | Examples |
-|----------|----------|
-| **User Preferences** | Coding style, tool preferences, language choices |
-| **Procedure Outcomes** | Commands that worked, configurations that resolved issues |
-| **Learnings** | Bug solutions, workarounds, architecture decisions |
-
-## Architecture
-
-### Local Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-embed CLI
-    │
-    ▼
-Local Daemon (auto-started)
-    │
-    ▼
-Embedded PostgreSQL (~/.pg0/hindsight-embed/)
-```
-
-All data stays on your machine. The daemon auto-starts when needed and shuts down after inactivity.
-
-### Cloud Mode
-
-```
-AI Coding Assistant
-    │
-    ▼
-Hindsight Skill (SKILL.md)
-    │
-    ▼
-hindsight-cli
-    │
-    ▼
-Hindsight Cloud API (https://api.hindsight.vectorize.io)
-    │
-    ▼
-Shared Memory Bank (team-accessible)
-```
-
-Data is stored in Hindsight Cloud and shared across your team. All team members with the same bank ID can access shared memories.
-
---
-
-## Local Mode Setup
-
-The skill uses configuration stored in `~/.hindsight/config.env`. Reconfigure anytime:
-
-```bash
-uvx hindsight-embed configure
-```
-
---
-
-## Cloud Mode Setup
-
-Cloud mode connects to [Hindsight Cloud](https://ui.hindsight.vectorize.io/signup), allowing teams to share memories about a codebase. When one team member learns something, everyone benefits.
-
-### Prerequisites
-
-1. A Hindsight Cloud account ([sign up](https://ui.hindsight.vectorize.io/signup))
-2. An API key from your team admin
-3. A bank ID for your project (e.g., `team-acme-frontend`)
-
-### Installation
-
-Run the installer with cloud mode:
-
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-You'll be prompted for:
-
-| Setting | Description | Example |
-|---------|-------------|---------|
-| **Cloud API URL** | Hindsight Cloud endpoint | `https://api.hindsight.vectorize.io` |
-| **API Key** | Your authentication key | `hs_xxx...` |
-| **Bank ID** | Shared memory bank for your team | `team-acme-frontend` |
-
-### Configuration Files
-
-Cloud mode creates two files:
-
-**`~/.hindsight/config`** — API connection settings (TOML format):
-```toml
-api_url = "https://api.hindsight.vectorize.io"
-api_key = "hs_xxx..."
-```
-
-**`~/.claude/skills/hindsight/SKILL.md`** — Skill definition with your bank ID baked in.
-
-### Team Setup
-
-To set up cloud mode for your team:
-
-1. **Team admin** creates a bank in Hindsight Cloud (e.g., `team-acme-frontend`)
-2. **Team admin** generates API keys for each team member
-3. **Each developer** runs the installer with their API key and the shared bank ID
-4. All team members now share the same memory bank
-
-### What to Store in Team Banks
-
-Cloud mode uses a **shared team bank**. Be thoughtful about what goes in:
-
-| Type | Examples | How to Store |
-|------|----------|--------------|
-| **Project conventions** | Linting rules, testing requirements, Node version | `"Project uses ESLint with Airbnb config"` |
-| **Team knowledge** | Architecture decisions, common pitfalls, domain logic | `"Auth module requires Redis 7+"` |
-| **Individual preferences** | Personal coding style, communication preferences | `"Alice prefers verbose commit messages"` |
-
-**Key distinction**: Project conventions apply to everyone. Individual preferences should include the person's name so the AI knows when to apply them.
-
-### Example Workflow
-
-```
-Day 1: Alice discovers a requirement
-─────────────────────────────────────
-Alice's AI assistant stores:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-  "Alice prefers explicit error handling over silent failures"
-
-Day 2: Bob starts working on auth
-─────────────────────────────────
-Bob's AI assistant recalls:
-  "The auth module requires Redis 7+ due to HEXPIRE command usage"
-
-Bob avoids the same issue Alice hit!
-(Alice's personal preference is stored but won't be applied to Bob)
-```
-
-### Testing Cloud Connection
-
-After installation, verify the connection:
-
-```bash
-# Store a test memory
-hindsight memory retain team-acme-frontend "Alice works at Google as a software engineer"
-
-# Recall it
-hindsight memory recall team-acme-frontend "Alice"
-```
-
-### Switching Between Banks
-
-If you work on multiple projects, you can have different skills installed for each AI assistant, or manually switch banks:
-
-```bash
-# Environment variable override (temporary)
-HINDSIGHT_API_URL=https://api.hindsight.vectorize.io \
-HINDSIGHT_API_KEY=hs_xxx \
-hindsight memory recall different-bank "query"
-```
-
-For permanent multi-bank setups, reinstall the skill with a different bank ID.
-
-## Troubleshooting
-
-### Skill not activating
-
-The skill activates based on its description matching your request. Try being explicit:
- "Remember that..." triggers storage
- "What do you know about..." triggers recall
-
-### Local Mode Issues
-
-**Daemon not starting:**
-```bash
-uvx hindsight-embed daemon status
-uvx hindsight-embed daemon logs
-```
-
-**Reconfigure LLM provider:**
-```bash
-uvx hindsight-embed configure
-```
-
-### Cloud Mode Issues
-
-**Authentication errors:**
-```bash
-# Verify your config
-cat ~/.hindsight/config
-
-# Test connection manually
-hindsight bank list
-```
-
-**Wrong bank ID:**
-
-Check your SKILL.md file to see which bank ID is configured:
-```bash
-cat ~/.claude/skills/hindsight/SKILL.md | grep "memory retain"
-```
-
-To change the bank ID, reinstall the skill:
-```bash
-curl -fsSL https://hindsight.vectorize.io/get-skill | bash -s -- --mode cloud
-```
-
-**Network/firewall issues:**
-```bash
-# Test connectivity to cloud API
-curl -I https://api.hindsight.vectorize.io/health
-```
-
-## Requirements
-
-### Local Mode
- Python 3.10+ (for `uvx`)
- An LLM API key (OpenAI, Anthropic, Groq, etc.)
-
-### Cloud Mode
- Python 3.10+ (for `uvx`)
- Hindsight Cloud API key
- Network access to `https://api.hindsight.vectorize.io`
@@ -1,157 +0,0 @@
---
-sidebar_position: 13
-title: "Strands Agents Persistent Memory with Hindsight | Integration"
-description: "Add long-term memory to Strands Agents SDK agents with Hindsight. Retain, recall, and reflect tools using Strands' native @tool pattern for persistent memory across sessions."
---
-
-# Strands Agents
-
-Persistent memory tools for [Strands Agents SDK](https://github.com/strands-agents/sdk-python) agents via Hindsight. Give your agents long-term memory with retain, recall, and reflect — using Strands' native `@tool` pattern.
-
-## Features
-
- **Native `@tool` Functions** - Tools are plain Python functions, compatible with `Agent(tools=[...])`
- **Memory Instructions** - Pre-recall memories for injection into agent system prompt
- **Three Memory Tools** - Retain (store), Recall (search), Reflect (synthesize) — include any combination
- **Simple Configuration** - Configure once globally, or pass a client directly
-
-## Installation
-
-```bash
-pip install hindsight-strands
-```
-
-## Quick Start
-
-```python
-from strands import Agent
-from hindsight_strands import create_hindsight_tools
-
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-agent = Agent(tools=tools)
-agent("Remember that I prefer dark mode")
-agent("What are my preferences?")
-```
-
-The agent now has three tools it can call:
-
- **`hindsight_retain`** — Store information to long-term memory
- **`hindsight_recall`** — Search long-term memory for relevant facts
- **`hindsight_reflect`** — Synthesize a reasoned answer from memories
-
-## With Memory Instructions
-
-Pre-recall relevant memories and inject them into the system prompt:
-
-```python
-from hindsight_strands import create_hindsight_tools, memory_instructions
-
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-memories = memory_instructions(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-)
-
-agent = Agent(
-    tools=tools,
-    system_prompt=f"You are a helpful assistant.\n\n{memories}",
-)
-```
-
-## Selecting Tools
-
-Include only the tools you need:
-
-```python
-tools = create_hindsight_tools(
-    bank_id="user-123",
-    hindsight_api_url="http://localhost:8888",
-    enable_retain=True,
-    enable_recall=True,
-    enable_reflect=False,  # Omit reflect
-)
-```
-
-## Global Configuration
-
-Instead of passing connection details to every call, configure once:
-
-```python
-from hindsight_strands import configure, create_hindsight_tools
-
-configure(
-    hindsight_api_url="http://localhost:8888",
-    api_key="your-api-key",       # Or set HINDSIGHT_API_KEY env var
-    budget="mid",                  # Recall budget: low/mid/high
-    max_tokens=4096,               # Max tokens for recall results
-    tags=["env:prod"],             # Tags for stored memories
-    recall_tags=["scope:global"],  # Tags to filter recall
-    recall_tags_match="any",       # Tag match mode: any/all/any_strict/all_strict
-)
-
-# Now create tools without passing connection details
-tools = create_hindsight_tools(bank_id="user-123")
-```
-
-## Configuration Reference
-
-### `create_hindsight_tools()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `budget` | `"mid"` | Recall/reflect budget level (low/mid/high) |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `tags` | `None` | Tags applied when storing memories |
-| `recall_tags` | `None` | Tags to filter when searching |
-| `recall_tags_match` | `"any"` | Tag matching mode |
-| `enable_retain` | `True` | Include the retain (store) tool |
-| `enable_recall` | `True` | Include the recall (search) tool |
-| `enable_reflect` | `True` | Include the reflect (synthesize) tool |
-
-### `memory_instructions()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `bank_id` | *required* | Hindsight memory bank ID |
-| `client` | `None` | Pre-configured Hindsight client |
-| `hindsight_api_url` | `None` | API URL (used if no client provided) |
-| `api_key` | `None` | API key (used if no client provided) |
-| `query` | `"relevant context about the user"` | Recall query for memory injection |
-| `budget` | `"low"` | Recall budget level |
-| `max_results` | `5` | Maximum memories to inject |
-| `max_tokens` | `4096` | Maximum tokens for recall results |
-| `prefix` | `"Relevant memories:\n"` | Text prepended before memory list |
-| `tags` | `None` | Tags to filter recall results |
-| `tags_match` | `"any"` | Tag matching mode |
-
-### `configure()`
-
-| Parameter | Default | Description |
-|---|---|---|
-| `hindsight_api_url` | Production API | Hindsight API URL |
-| `api_key` | `HINDSIGHT_API_KEY` env | API key for authentication |
-| `budget` | `"mid"` | Default recall budget level |
-| `max_tokens` | `4096` | Default max tokens for recall |
-| `tags` | `None` | Default tags for retain operations |
-| `recall_tags` | `None` | Default tags to filter recall |
-| `recall_tags_match` | `"any"` | Default tag matching mode |
-| `verbose` | `False` | Enable verbose logging |
-
-## Requirements
-
- Python >= 3.10
- strands-agents
- hindsight-client >= 0.4.0
- A running Hindsight API server