mex

mex-memory/mex

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

Install

Keep your team's architecture, decisions, requirements and handoffs in the repo, shared through Git
Let engineers and agents build on shared context and review proposed knowledge changes
Record how the system works and why, in readable Markdown linked to code

Run npx mex-agent@0.8.4 setup (it installs the Inbox and Relay skills for your chosen Claude Code or Codex)
Complete setup in the terminal HUD, then review in the local Hub
Explore team memory in the Hub; agents retrieve and maintain it through project instructions and the CLI

Shared project memory that lives in the repo with Git as the sharing layer; upgrade the whole team before sharing a new format.

Summarized by AI from the project docs; check the official docs before relying on it.

open-stepsCommunity skills · ★ 1.2k
Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.
reaCommunity skills · ★ 380k
Reverse engineer anything with agents, from app behavior down to native binaries.
agent-skillsCommunity skills · ★ 110k
Production-grade engineering skills for AI coding agents.
taste-skillCommunity skills · ★ 102k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
archifyCommunity skills · ★ 88.8k
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.