Back to directory

memex

A Zettelkasten-based persistent memory system for AI coding agents that stores atomic, linked knowledge cards as plain markdown, shared across Claude Code, Cursor, Codex and other MCP clients.

memex

memex gives an AI coding agent persistent memory across sessions. When a task finishes, the agent saves what it learned as an atomic knowledge card with bidirectional links to related cards, and recalls relevant cards at the start of a later session instead of starting from scratch. It uses no vector database or embeddings, storing everything as markdown files any editor or agent can read.

It integrates with Claude Code as a plugin with hooks, skills and a session-start hook for automatic recall, and with VS Code Copilot, Cursor, Codex, Windsurf and other MCP clients as an MCP server exposing a dozen tools. All supported platforms share the same local card directory, so a card written in one editor is immediately available in another.

It is written in TypeScript and licensed under MIT.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.