Back to directory

MEX

Shared project memory for engineers and their coding agents, stored as reviewable Markdown in the repository itself and synced through ordinary Git commits.

MEX

MEX keeps a team's architecture decisions, requirements and handoffs alongside the code they describe, so what one engineer and their coding agent learn in a session becomes context the next teammate can use, instead of being lost in chat history. Knowledge lives as readable Markdown with code-linked explanations, reviewed knowledge contributions and structured handoffs; people explore and review it in a local hub, while agents retrieve and help maintain it through project instructions and the CLI.

It tracks several kinds of team memory: a wiki of architecture, decisions and conventions grounded against a code graph; inbox proposals that add to or correct existing wiki knowledge; specs, requirements and acceptance criteria; relay notes on progress, decisions, blockers and next actions for whoever continues the work; and a record of workstreams, members and activity. It installs with a single command that sets up official skills for Claude Code or Codex, uses tree-sitter for code-graph grounding, and is written in TypeScript under the MIT license.

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.