Mem0 plugin
Memory layer for agents: plugins for Claude Code, Codex, Cursor and OpenCode, plus a CLI and SDKs that carry context across sessions
- 68,059 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Sends session text and changed file paths to an external service
- Stores the Mem0 API key in plugin config
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/mem0Detects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Sends session text and changed file paths to an external service
- Stores the Mem0 API key in plugin config
This is third-party code. Review the repository files before installing.
What it does
Mem0 stores and retrieves memory for AI apps and coding agents. The Claude Code plugin uses hooks to capture messages, changed files and test results, a background worker turns them into Mem0 memories, and the next session starts with up to five relevant ones. Memory splits into shared project memory with conventions and working commands, and personal memory with your preferences. Similar plugins exist for Codex, Cursor, OpenCode, Kimi and Antigravity, and the mem0 and mem0-cli skills teach agents to add memory to apps via the Python and TypeScript SDKs.
Who it is for. For developers annoyed that agents forget the project between sessions, and for those adding memory to their own AI apps.
Good fit when
- The agent relearns build commands and project conventions every session
- A team needs shared agent memory per repository
- You need long-term memory in a chatbot or custom agent
Not a fit when
- Session content cannot go to an external service
- A hand-written CLAUDE.md or AGENTS.md is enough
Example request
Remember that tests in this project run with pnpm test:unit, not npm testLimitations
Agent plugins need a Mem0 Platform key, i.e. the api.mem0.ai cloud service. A fully local setup is only possible with the open-source library or a self-hosted Docker server. Secrets are redacted before sending, but full message text goes to the service.
How to disable. Run claude plugin uninstall mem0@mem0-plugins. Remove the CLI with npm uninstall -g @mem0/cli.
FAQ
Can it run without the cloud?
Agent plugins need a platform key. The mem0ai library and a docker compose server can be self-hosted.
How does an agent get a key without signup?
The README describes mem0 init --agent, which issues a working key to the agent that a person can later claim by email.
Discussion
No questions or reviews yet.
Related
PluginsShared local memory for AI agents: Claude Code, Codex, Cursor and others find the agreements of past sessions in it and record new ones
A long-term memory plugin that keeps decisions, preferences and task state across sessions and injects only what a query needs
Long-term memory for agents: a remote MCP server, plugins for Claude Code, Cursor and Codex, and an API for your own apps
A Claude Code skill that pulls memory from Memori Cloud before every non-trivial answer and writes new facts back to it
Local persistent memory for coding agents: hooks record every session, and Claude Code, Codex or Cursor recall past decisions through 54 MCP tools
Long-term memory for AI agents: Markdown files as the source of truth, a SQLite index as a cache, shared by Claude Code, Codex and others
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Mem0 (this entry) | no | 68,059 | ||
| memory-lancedb-pro | no | 4,451 | a long-term memory plugin for the OpenClaw agent on LanceDB | |
| Engram by Gentleman Programming | no | not required | 7,679 | persistent memory for AI coding agents in a single Go binary |
| Beacon | no | 2,921 | a CLI that records session history from Claude Code |
README in short
The README opens with benchmark results for the new memory algorithm on LoCoMo and LongMemEval. Quick start shows the CLI with agent signup, then compares three options: library, self-hosted server and cloud platform. It covers pip and npm installs, running the server with docker compose and integrations with agent frameworks. Apache-2.0 licensed.