mex

Provides persistent project memory for AI coding agents.

MCPDevOpen source

Type: MCP
Transport: stdio
Open source: Yes
GitHub Stars: ★ 1.2k
Source: mcp-github
Repository: github.com/mex-memory/mex

Overview

mex offers persistent project memory for AI coding agents, enabling each session to start with the correct context. It creates a structured Markdown architecture including routing tables, architecture diagrams, and decision logs, and uses CLI to detect and sync drifts in the codebase. This allows AI agents to remember prior decisions and patterns, avoid redundant work, and maintain consistency between documentation and code. Ideal for projects and teams requiring long-term maintenance.

Capabilities

▪Persistent project memory
▪Structured Markdown architecture
▪Drift detection
▪Automatic context updates

Use cases

AI agent codingProject documentation managementCodebase consistency checking

Setup

Requires: Node.js >=20API Key

npx mex-agent setup

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How do I install mex?

Run `npx mex-agent setup` to install.

Which operating systems does mex support?

Supports Windows, macOS, and Linux.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP