Connect Hindsight to your stack. Browse official integrations and community-built connectors.
One memory plugin for CLI coding agents — Claude Code, Codex, opencode, Kilo, Cursor, Copilot, Grok, Antigravity, Devin and Cline. Per-repo banks built automatically from git history and past sessions.




Add persistent memory to Vercel AI SDK applications. Works with any model provider supported by the AI SDK.
Persistent long-term memory for the Aider pair-programming CLI. hindsight-aider recalls relevant project memory before each session and retains the transcript after.
Add Hindsight memory to Claude Code agents via the Skills integration. Persistent context across coding sessions.
Long-term memory for the Continue.dev coding assistant. Recall relevant project memory into chat with @hindsight, plus optional automatic recall/retain via the Hindsight MCP server.
Biomimetic long-term memory for the Cursor editor via Hindsight. Recalls relevant context at session start and retains conversation transcripts for future sessions.
Long-term memory for Devin Desktop (the editor formerly known as Windsurf) via its native MCP support. One command wires the Hindsight MCP server into mcp_config.json plus an always-on recall/retain rule, so memory works automatically.
Long-term memory for GitHub Copilot in VS Code. One command wires the Hindsight MCP server into .vscode/mcp.json plus a recall/retain rule in .github/copilot-instructions.md.
Automatic long-term memory for Grok Build (xAI) via Hindsight hooks. Captures every conversation, recalls relevant context on every prompt.
Automatic long-term memory for OMO agent harness via Hindsight hooks. Recalls context before each prompt and retains session learnings — zero config for cloud users.
Long-term memory for OpenHands (formerly OpenDevin) via its native MCP support. One command wires the Hindsight MCP server into config.toml plus a recall/retain rule.
Persistent memory for Roo Code via Hindsight MCP. Auto-recalls context before each task and retains learnings after.
No-MCP long-term memory for ZCode (Z.ai's GLM desktop coding agent) via Hindsight hooks. Recalls relevant context before each prompt and retains conversations after each turn.
Persistent long-term memory for AG2 agents with retain, recall, and reflect tools across conversations.
Give AutoGen agents persistent long-term memory with Hindsight FunctionTool instances for retain, recall, and reflect.
Persistent memory for Amazon Bedrock AgentCore Runtime agents. Memory survives ephemeral Runtime sessions so agents remember users, decisions, and context across reprovisioning.
Persistent long-term memory for Anthropic's Claude Agent SDK. Drop-in MCP memory tools plus hooks so Claude agents recall and retain context across sessions.
Hindsight memory as Composio custom tools. Retain, recall, and reflect drop into any Composio agent — memory is isolated per session user automatically.
Give CrewAI agents persistent, cross-session memory. Facts learned in one run are available in every future run.
Persistent memory plugin for Dify workflows. Retain, Recall, and Reflect tools drop into any chatflow or agent app alongside Dify's other LLM and tool nodes.
Give elizaOS agents long-term memory. A plugin that recalls relevant memories into the prompt and retains conversations to Hindsight.
Automatic long-term memory for Vercel Eve agents. Memory is injected before each turn and retained after, with no model tool-calling.
Drop-in Hindsight tool nodes for Flowise visual chatflows and agents. Retain, Recall, and Reflect work alongside any LangChain agent in the canvas.
Persistent memory for Google ADK agents. Implements BaseMemoryService for automatic retain on session end and recall on search_memory, plus explicit FunctionTool wrappers.
Persistent memory for Haystack agents. Provides retain/recall/reflect Tools plus a HindsightMemoryWrapper with optional auto-recall and auto-retain.
Production memory infrastructure for AI agents — server-side access control via Hindsight extensions, Terraform provider for users/groups/banks/permissions, and an OpenClaw plugin with auto-managed embed.
Add persistent memory to LangGraph and LangChain agents. Supports Memory Tools, Graph Nodes, and BaseStore adapter patterns.
Add long-term memory to any LLM via LiteLLM proxy callbacks. Zero code changes — configure once and every model gets memory.
Add persistent memory to LlamaIndex agents. Supports agent-driven tools (BaseToolSpec) and automatic memory (BaseMemory).
Persistent memory for Microsoft Agent Framework (the successor to Semantic Kernel) via a context provider that auto-recalls and auto-retains each turn.
Persistent memory community node for n8n workflows. Retain, recall, and reflect operations drop into any workflow alongside Slack, Sheets, OpenAI, and 400+ other integrations.
Give every harness you run in Omnigent persistent memory. One setup wires memory_recall, memory_retain, and memory_reflect across Claude Code, Codex, Cursor, Hermes, Pi, and any custom agent.
Give OpenAI Agents SDK agents persistent long-term memory with Hindsight FunctionTool instances for retain, recall, and reflect.
Integrate Hindsight memory into Pydantic AI agents with a simple dependency injection pattern.
Persistent memory for Right Agent — closed-box AI agents that run Claude Code inside OpenShell sandboxes. Hindsight is the native memory provider, selected during initialization.
Give HuggingFace SmolAgents persistent long-term memory with Hindsight retain, recall, and reflect tools.
Give Strands agents persistent long-term memory with Hindsight retain, recall, and reflect tools.
Governance-aware agent memory — importance-weighted storage of AI agent governance decisions. Critical denials persist for compliance; routine approvals decay naturally.
Drop-in memory layer for the Vercel AI Chatbot. Remembers users across sessions out of the box.
Register Hindsight as an MCP backend in ContextForge gateway. Gives every connected AI tool access to long-term memory via a unified MCP hub.
Expose Hindsight memory as a Model Context Protocol server. Compatible with Claude, Cursor, and any MCP client.
Portable long-term memory for any Agent Plugins client (Codex, Cursor, GitHub Copilot, Kiro, VS Code). One standards-based plugin bundles Hindsight's MCP server and a memory skill — recall, retain, and reflect everywhere.
Turns your local notes into long-term memory any agent can recall over MCP — with automatic sync, folder-scoped recall, and living summaries.
Add persistent long-term memory to ChatGPT via OAuth-secured MCP connectors. Store insights from conversations and recall relevant context across sessions.
Memory for pi coding agent. Retain, recall, reflect, past-session ingestion, and much more, with a focus on flexibility and memory quality/best practices.
Persistent memory for Google's Gemini Spark assistant via MCP. Spark calls Hindsight's recall and retain tools through its built-in MCP client — works with Hindsight Cloud or self-hosted via an OAuth proxy.
Configure Hindsight as your memory provider directly in the Hermes desktop app — pick a mode, paste an API key, no config files.
Persistent memory for NemoClaw sandboxed agents. One-command setup — no code changes required.
Sync your Obsidian vault into Hindsight and chat with an agent grounded on your notes. Your vault stays the source of truth — every answer cites the note it came from.
Persistent memory for Paperclip AI agents. Install the plugin once and every agent gets automatic recall before runs and retain after — no code changes.
Add persistent long-term memory to Perplexity via OAuth-secured MCP connectors. Store research findings and recall relevant context across searches.
Persistent memory for Pipecat voice AI pipelines via a FrameProcessor that recalls context before each turn and retains conversation content after.
Safety middleware for Hindsight memory operations via Superagent. Guards against prompt injection and redacts PII before content is stored.
Share your integration with the community. Open a pull request and add your entry to the integrations list.
Submit an integration →