#598 · Primary category: AI Agents & Automation

memmy-agent

agent agentic-ai ai-agents chatgpt claude-code cli codex cursor desktop-app desktop-pet dsh-plugin hermes-agent llm long-term-memory mcp memory openai-api openclaw personal-ai tui

🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex, OpenClaw and Hermes Agent etc.

Project last updated:08/28/26

GitHub Stars

1.2K

Forks

105

Contributors

26

License

MIT

Why we included this project

If you work with several coding agents and are tired of re-explaining your project to each one, Memmy is worth a look. It keeps a local memory layer that records project goals, decisions, constraints, and past failures, then hands that context to whatever agent you open next, whether that is Claude Code, Codex, Cursor, or OpenClaw. The memory engine turns scattered conversations and work history into searchable long-term knowledge, and it can pull in the existing history of your current agents so you start with context rather than a blank slate. On top of the memory hub, it includes a local agent runtime with a desktop app, CLI/TUI, and an OpenAI-compatible API, plus MCP and custom Skills for wiring up tools like GitHub, Slack, and messaging channels. Data stays on your machine by default, which is the point if you want persistent context without sending your memory to a cloud service.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category