OpenMemory

Active
GitHub TypeScript Apache-2.0

Description

Local persistent memory store for LLM applications including Claude Desktop, GitHub Copilot, Codex, and more. Provides durable context memory capabilities for AI agents.

Key Features

  • Multi-sector cognitive memory: episodic, semantic, procedural, emotional, reflective
  • Temporal knowledge graph with valid_from/valid_to for time-aware recall
  • Self-hosted local-first storage via SQLite or Postgres, no vendor lock-in
  • Python and Node SDKs with integrations for LangChain, CrewAI, AutoGen, MCP
  • Explainable recall traces showing which memory nodes were used and why
  • Data connectors for GitHub, Notion, Google Drive, OneDrive, and web crawlers

Use Cases

💡 Give AI agents persistent long-term memory across conversations and sessions
💡 Replace cloud-based vector DB memory with a local self-hosted alternative
💡 Build context-aware AI applications that remember user preferences and history
💡 Ingest and index knowledge from multiple sources for agent retrieval

Tags

memory typescript agent tools

Categories

🧩 Agent Memory

Quick Start

Python: `pip install openmemory-py` then `from openmemory.client import Memory; mem = Memory(); mem.add('user prefers dark mode', user_id='u1')`. Node: `npm install openmemory-js`. For server mode: `git clone` the repo, `cp .env.example .env`, then `docker compose up --build`. Backend exposes REST API, MCP server, and optional dashboard.
Visit GitHub Visit Website

Related Projects

Related Articles

Memory记忆系统长期记忆

Agent Memory Architecture: Working, Long-term, and Shared Memory Trade-offs

A systematic comparison of the three categories of agent memory -- working, long-term, and shared -- covering storage media, lifecycle, retrieval methods, typical frameworks, and design patterns, fully addressing agent personalization and multi-agent collaboration engineering.

Read more →
AI Agent记忆系统向量检索

Designing Agent Memory Systems: From Short-Term Context to Persistent Knowledge

A deep dive into the four-layer agent memory architecture, with practical code for vector retrieval and memory compression to help you build scalable long-term memory systems.

Read more →