Files
vectorize-io__hindsight/hindsight-integrations
xiaoxiao 0eee31b63c fix(openclaw): inject [doc:<document_id>] provenance into auto-recall memories (#3583)
* fix(openclaw): inject [doc:<document_id>] provenance into auto-recall memories

formatMemories previously dropped document_id before injection, so recalled
memories carried no source-session marker and another session/channel
memories could be mistaken for current context. Append [doc:<document_id>]
to each memory bullet when present; observations (no document_id) stay
unmarked and keep mentioned_at. Signature unchanged - no config, types, or
call-site changes.

Fixes #3582

* fix(openclaw): also inject the occurred window into auto-recall memories

`formatMemories` dropped `occurred_start`/`occurred_end` along with
`document_id`. `mentioned_at` only says when a fact was stated, so with the
event window gone the agent cannot order past events against each other —
"visited Paris" and "deployed the indexer" both read as whatever date they
happened to be mentioned on.

Each bound can be absent independently, so the wording is per-case
(`[occurred: X]`, `[occurred: X → Y]`, `[occurred from: X]`,
`[occurred until: Y]`) rather than a half-empty range the model has to
interpret.

---------

Co-authored-by: Nicolò Boschi <boschi1997@gmail.com>
2026-08-19 16:13:50 +02:00
..

Hindsight Integrations

First-party integrations that give popular AI agents, frameworks, and CLIs persistent long-term memory via Hindsight.

Each integration lives in its own subdirectory with its own README, configuration, and tests. Pick the one that matches the agent or framework you're using.

Coding agents & CLIs

Integration What it does Install
Claude Code Hooks-based memory for Anthropic's Claude Code. Auto-retains every session, recalls context on each prompt. npx hindsight-cc
OpenCode TypeScript plugin with retain/recall/reflect tools, auto-retain on idle, memory injection on session start, compaction preservation. Add @vectorize-io/opencode-hindsight to opencode.json
Codex CLI Python hook scripts for OpenAI's Codex CLI. Auto-recall on UserPromptSubmit, auto-retain on Stop. curl -fsSL https://hindsight.vectorize.io/get-codex | bash
Cursor CLI Python hook scripts for Cursor CLI. Auto-recall on beforeSubmitPrompt, auto-retain on stop, final flush on sessionEnd. ./scripts/install.sh
Copilot CLI Python hook scripts for GitHub Copilot CLI. Auto-recall on sessionStart/subagentStart, auto-retain on agentStop, final flush on sessionEnd. pip install hindsight-copilot-cli && hindsight-copilot-cli install
Continue.dev HTTP context provider for precise @hindsight recall in chat, plus optional MCP-server + rules for automatic recall/retain in agent mode. pip install hindsight-continue
GitHub Copilot (VS Code) MCP server config (.vscode/mcp.json) + a recall/retain rule for VS Code Copilot's agent mode. pip install hindsight-copilot
Devin Desktop Native MCP server config + always-on recall/retain rule for Devin Desktop (formerly Windsurf). pip install hindsight-devin-desktop
Roo Code Persistent memory for Roo Code VS Code extension. See README
Hermes (OpenAI Agents SDK) Memory layer for OpenAI Agents SDK. See README
Grok Build Hooks for Grok Build (xAI). See README
Claude Code Skills Skills integration for Claude Code agents. See README

Agent frameworks

Integration What it does
LiteLLM Proxy callbacks — every model proxied through LiteLLM gets memory. Zero code changes.
CrewAI Long-term memory tools for CrewAI agents.
Pydantic AI Dependency-injected memory for Pydantic AI agents.
Vercel AI SDK Persistent memory for Vercel AI SDK apps.
Vercel Chat Drop-in memory for the Vercel AI Chatbot.
LangGraph / LangChain Memory Tools, Graph Nodes, and BaseStore adapter patterns.
LlamaIndex Agent-driven (BaseToolSpec) and automatic (BaseMemory) memory.
Google ADK BaseMemoryService implementation for ADK.
Strands Agents Retain/recall/reflect tools for Strands.
AG2 Cross-conversation memory tools.
AutoGen FunctionTool instances for retain/recall/reflect.
Aider hindsight-aider wraps the aider CLI — recalls project memory before each session, retains the transcript after.
OpenAI Agents SDK FunctionTool-based memory.
OpenHands Native MCP server config + recall/retain rule for OpenHands (formerly OpenDevin).
NemoClaw One-command setup for NemoClaw sandboxes.
Right Agent Native memory provider for Right Agent sandboxes.
Pipecat Memory nodes for Pipecat voice pipelines.
AgentCore Memory tools for AgentCore agents.
Smolagents Retain/recall/reflect tools for HuggingFace Smolagents.
OpenClaw Memory for OpenClaw workflows.

Workflow & automation platforms

Integration What it does
n8n Community node — drop retain/recall/reflect into any n8n workflow.
Zapier Zapier app — retain/recall/reflect actions plus instant memory-event triggers.
Dify Persistent memory for Dify apps.
Flowise Memory nodes for Flowise flows.
Vapi Persistent memory for Vapi voice agents.
Gemini Spark Memory for Gemini Spark.
Roo Code Memory for the Roo Code VS Code extension.
Google ADK BaseMemoryService for Google ADK.
Cloudflare OAuth Proxy OAuth proxy so you can run Hindsight behind Cloudflare Access.
Paperclip Memory layer for Paperclip workflows.

Adding a new integration

See CLAUDE.md → "Adding New Integrations" for the checklist (tests, CI job, release registration, code standards).

Releases

Each integration is versioned and released independently:

./scripts/release-integration.sh <integration-name> <version>
# e.g.
./scripts/release-integration.sh cursor-cli patch

The release script reads the version from the integration's settings.json / package.json / pyproject.toml, generates a changelog entry, and tags integrations/<name>/v<version>.