iamtouchskyer/memex
Zettelkasten-based persistent memory for AI coding agents. Works with Claude Code, Cursor, VS Code Copilot, Codex, Windsurf & any MCP client. No vector DB — just markdown + git sync.
This project helps software developers make their AI coding agents smarter by giving them a persistent memory. When an AI agent completes a task, it saves key insights as simple markdown knowledge cards. In future sessions, the agent can recall these relevant cards, allowing it to build on past knowledge rather than starting from scratch.
Use this if you are a software developer using AI coding agents (like those in Claude Code, VS Code Copilot, Cursor) and want them to remember past learnings and improve their performance across different coding sessions.
Not ideal if you're looking for a traditional knowledge base for human use or if your workflow does not involve AI coding agents.
Stars
49
Forks
9
Language
TypeScript
License
MIT
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/iamtouchskyer/memex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude....
Dataojitori/nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to...
spences10/mcp-memory-libsql
🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL....
gannonh/memento-mcp
Memento MCP: A Knowledge Graph Memory System for LLMs
mkreyman/mcp-memory-keeper
MCP server for persistent context management in AI coding assistants