Mex
Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.
Install
npx skills add mex-memory/mex -a claude-code
npx skills add mex-memory/mex -a claude-code -g
Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).
npx skills add mex-memory/mex -a codex
npx skills add mex-memory/mex -a codex -g
Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).
npx skills add mex-memory/mex -a cursor
npx skills add mex-memory/mex -a cursor -g
Or copy the skill folder into .agents/skills/ (project) or ~/.cursor/skills/ (all projects).
See the repository README for installation instructions.
When to use
Use it when several people and agents work in one repo and you want decisions and context kept in Git instead of in chat history.
mex is shared project memory for engineers and their coding agents. Memory lives as Markdown in a .mex/ folder, travels with Git and stays linked to the code, so a teammate or a new agent session picks up what was decided. There's a local Hub for people to browse it, and a CLI and skills for agents.
Run npx [email protected] setup to install. The README includes a teammate-handoff example showing how one engineer's context passes to the next, and mentions an MCP server and an agent memory mode. It works with Claude Code, Cursor and Codex, and the README is translated into several languages.
Related skills
-
rea
Lets your agent reverse engineer an app from the outside, down to native binaries, and then build its own version.
-
superpowers
A set of development habits for your agent: test first, debug systematically, and plan before you code.
-
skills
The skills Matt Pocock uses in his own day-to-day engineering work.
-
ECC
A ready-made setup for coding agents that adds skills, persistent memory and security checks.