mex — Agent Tool by theDakshJaitly

by theDakshJaitly · Agent Tool · ★ 684

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About mex

mex AI agents forget everything between sessions. mex gives them permanent, navigable project memory. Every session starts cold: The agent has no idea what it built yesterday It forgets the conventions you agreed on It doesn't know what broke last week Developers compensate by stuffing everything into CLAUDE.md — but that floods the context window, burns tokens, and degrades attention. Meanwhile, the project changes and nobody updates the docs. The agent's understanding drifts from reality. mex is a structured markdown scaffold with a CLI that keeps it honest. The scaffold gives agents persistent project knowledge through navigable files — architecture, conventions, decisions, patterns. The CLI detects when those files drift from the actual codebase, and targets AI to fix only what's broken. The scaffold grows automatically — after every task, the agent updates project

claude-codeclaude-code-skillscli-toolcontext-managementcursordeveloper-toolsdocumentationllm

Quick Facts

Stars684
Forks41
LanguageTypeScript
CategoryAgent Tool
LicenseMIT
Quality Score59.084/100
Open Issues6
Last Updated2026-04-24
Created2026-03-21
Platformsclaude-code, cli, node
Est. Tokens~25k

Compatible Skills

These tools work well together with mex for enhanced workflows:

  • ris-claude-code — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

mex alternative? Top 6 similar tools

Looking for a mex alternative? If you're comparing mex with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • cortex-tms by cortex-tms · ⭐ 170

    The Universal AI-Optimized Project Boilerplate. A Tiered Memory System (TMS) designed to maximize AI agent per

  • pro-workflow by rohitg00 · ⭐ 2.0k

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng

  • Observal by BlazeUp-AI · ⭐ 844

    Observal is an AI agent registry with first in class observabilty and eval framework

  • OpenContext by 0xranx · ⭐ 413

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • ctx by stevesolun · ⭐ 303

    Skill, agent, MCP, and harness catalog for Claude Code/custom LLMs: 104,078-node LLM-wiki graph, 92,815 skills

  • smart-ralph by tzachbon · ⭐ 276

    Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular TypeScript Agent Tools

  • openclaw ⭐ 368.6k · Codex Skill
  • n8n ⭐ 186.8k · MCP Server
  • dify ⭐ 140.2k · MCP Server
  • gemini-cli ⭐ 103.2k · MCP Server
  • gstack ⭐ 89.6k · Agent Tool

Frequently Asked Questions

What is mex?

mex is Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI.. It is categorized as a Agent Tool with 684 GitHub stars.

What programming language is mex written in?

mex is primarily written in TypeScript. It covers topics such as claude-code, claude-code-skills, cli-tool.

How do I install or use mex?

You can find installation instructions and usage details in the mex GitHub repository at github.com/theDakshJaitly/mex. The project has 684 stars and 41 forks, indicating an active community.

What license does mex use?

mex is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to mex?

The top alternatives to mex on Agent Skills Hub include cortex-tms, pro-workflow, Observal. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse Agent Tool tools