mirror of
https://github.com/vectorize-io/hindsight.git
synced 2026-09-14 19:31:49 +08:00
6500944c74
* feat(copilot-cli): add GitHub Copilot CLI hooks integration Add hindsight-integrations/copilot-cli/, giving GitHub Copilot CLI persistent long-term memory via Hindsight hooks (see docs.github.com/en/ copilot/how-tos/copilot-cli/customize-copilot/use-hooks). Modeled on the existing cursor-cli integration. Hooks: - sessionStart: recall using initialPrompt (or a cwd-derived fallback query), injects additionalContext - subagentStart: recall for every subagent Copilot CLI spawns (explore, task, research, code-review, rubber-duck, security-review, and custom agents, not the built-in general-purpose agent, which never fires this hook). Subagent payloads carry no per-invocation task text, so this always uses the fallback query. - agentStop: reads the transcript, retains to Hindsight on a configurable turn cadence, caches the transcript path for sessionEnd - sessionEnd: forces a final retain using the transcript path cached from the last agentStop, since sessionEnd's own payload has no transcript path field Install via pip install hindsight-copilot-cli, then hindsight-copilot-cli install (user scope, writes ~/.copilot/hooks/hindsight-copilot-cli.json) or --scope repo for a team-shared .github/hooks/ registration. Zero runtime dependencies, hook scripts are pure stdlib Python. Also wires up CI (test-copilot-cli-integration job), release-integration.sh and generate_changelog.py registration, and docs gallery/sidebar entry. Closes #1588 * fix(copilot-cli): regen skill mirror, drop unreleased changelog link - Run generate-docs-skill.sh to add the missing skill mirror for the new copilot-cli doc page (verify-generated-files was failing on the untracked references/sdks/integrations/copilot-cli.md). - Remove the [View Changelog] link, which pointed at /changelog/integrations/copilot-cli — a page the release script only creates on first release, so it was a broken link failing build-docs.
5.5 KiB
5.5 KiB
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>.