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.
Every time your AI agent finishes a task, it saves insights as atomic knowledge cards with [[bidirectional links]]. Next session, it recalls relevant cards before starting work — building on what it already knows instead of starting from scratch.
No vector database, no embeddings — just markdown files your agent (and you) can read.
Supported platforms
| Platform | Integration | Experience |
|----------|------------|------------|
| Claude Code | Plugin (hooks + skills) | Best — auto-recall, slash commands, SessionStart hook |
| VS Code / Copilot | MCP Server | 10 MCP tools, zero config |
| Cursor | MCP Server | 10 MCP tools, zero config |
| Codex | MCP Server | 10 MCP tools, zero config |
| Windsurf | MCP Server | 10 MCP tools, zero config |
| Pi | Extension (custom tools + hooks) | 8 tools, auto-recall hook, slash commands |
| Any MCP client | MCP Server | 10 MCP tools, zero config |
All platforms share the same ~/.memex/cards/ directory. A card written in Claude Code is instantly available in Cursor, Codex, or any other client.
Prerequisites
VS Code / Copilot: No prerequisites — the extension bundles everything
Claude Code: No prerequisites — the plugin handles everything
Pi: Requires Node.js 18+ and npm install -g @touchskyer/memex
All other platforms (Cursor, Codex, Windsurf, etc.): Requires Node.js 18+
Install
Step 1: Add memex to your editor
| Platform | Command |
|----------|---------|
| VS Code / Copilot | Search "memex" in VS Code Extensions — install and done, no extra setup |
| Claude Code | /plugin marketplace add iamtouchskyer/memex then /plugin install memex@memex |
| Cursor | First npm install -g @touchskyer/memex, then one-click install |
| Codex | npm install -g @touchskyer/memex && codex mcp add memex -- memex mcp |
| Pi | npm install -g @touchskyer/memex && pi install npm:@touchskyer/memex |
| Windsurf / others | npm install -g @touchskyer/memex, then add MCP server: command memex, args ["mcp"] |
That's it — no extra setup needed. The MCP tool descriptions tell your agent when to recall and retro.
Upgrade
| Platform | How |
|----------|-----|
| VS Code / Copilot | Extension auto-updates from marketplace |
| Claude Code | /plugin uninstall memex then /plugin install memex@memex |
| Pi | npm update -g @touchskyer/memex and re-copy pi-extension/index.ts |
| Cursor / Codex / Windsurf | npm update -g @touchskyer/memex |
Cross-platform sharing
All clients read and write the same ~/.memex/cards/ directory. Sync across devices with git:
Prerequisite: Auto-create requires GitHub CLI (gh auth login). Or pass your own repo URL to skip this.
memex sync --init # auto-creates private memex-cards repo on GitHub
memex sync --init <repo-url> # or specify your own repo URL (no gh CLI needed)
memex sync on # enable auto-sync after every write
memex sync # manual sync
memex sync off # disable auto-sync
Browse your memory
memex serve
Opens a visual timeline of all your cards at localhost:3939. Includes a graph view to explore bidirectional links.
If you've set up sync, memex serve opens memra.vercel.app — a web UI with Timeline, Graph view, and Share card.
CLI reference
memex search [query] # search cards, or list all
memex read <slug> # read a card
memex write <slug> # write a card (stdin)
memex links [slug] # link graph stats
memex archive <slug> # archive a card
memex serve # visual timeline UI
memex sync # sync via git
memex mcp # start MCP server (stdio)
How it works
Based on Niklas Luhmann's Zettelkasten method — the system behind 70 books from 90,000 handwritten cards:
Atomic notes — one idea per card
Own words — forces understanding (the Feynman method)
Links in context — "this relates to [[X]] because..." not just tags
Keyword index — curated entry points to the card network
Cards are stored as markdown in ~/.memex/cards/. Open them in Obsidian, edit with vim, grep from terminal. Your memory is never locked in.
AI 코딩 에이전트를 위한 영구 메모리 시스템. 에이전트가 세션을 넘어 학습한 내용을 기억합니다.
에이전트가 작업을 완료할 때마다 [[양방향 링크]]가 포함된 원자적 지식 카드로 인사이트를 저장합니다. 다음 세션에서는 작업 시작 전에 관련 카드를 불러와, 처음부터가 아닌 기존 지식 위에 구축합니다.
벡터 데이터베이스도 임베딩도 필요 없습니다 — 에이전트(와 당신)가 읽을 수 있는 markdown 파일뿐입니다.
지원 플랫폼
| 플랫폼 | 통합 방식 | 경험 |
|--------|---------|------|
| Claude Code | Plugin (hooks + skills) | 최고 — 자동 리콜, 슬래시 명령, SessionStart hook |
| VS Code / Copilot | MCP Server | 10개 MCP 도구, 설정 불필요 |
| Cursor | MCP Server | 10개 MCP 도구, 설정 불필요 |
| Codex | MCP Server | 10개 MCP 도구, 설정 불필요 |
| Windsurf | MCP Server | 10개 MCP 도구, 설정 불필요 |
| Pi | Extension (커스텀 도구 + hooks) | 8개 도구, 자동 리콜 hook, 슬래시 명령 |
| 모든 MCP 클라이언트 | MCP Server | 10개 MCP 도구, 설정 불필요 |
모든 플랫폼이 동일한 ~/.memex/cards/ 디렉토리를 공유합니다. Claude Code에서 작성한 카드를 Cursor, Codex 또는 다른 클라이언트에서 즉시 사용할 수 있습니다.
전제 조건
VS Code / Copilot: 전제 조건 없음 — 확장 프로그램에 모든 것이 포함
Claude Code: 전제 조건 없음 — 플러그인이 모든 것을 처리
Pi: Node.js 18+ 및 npm install -g @touchskyer/memex 필요
기타 플랫폼 (Cursor, Codex, Windsurf 등): [Node.js 18+](https://nodej
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
