#443 · Primary category: AI Coding Assistants
brain.md
A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.
Project last updated:08/21/26
GitHub Stars
515
Forks
47
Contributors
8
License
Apache-2.0
Why we included this project
Coding agents lose the context of a long-running project the moment a session ends, and this tool gives them a persistent memory to carry forward. It defines a plain-Markdown standard: a BRAIN.md file and a brain/ directory that capture the durable decisions your team made, the requirements you've agreed on, and any constraints that should stick. A zero-dependency CLI reads and writes that memory, so a team can adopt it without standing up a backend or database. If you use Claude Code, Codex, or Cursor on real work, this stops architectural choices and agreed constraints from dissolving into chat logs, and the context stays with the repo regardless of which agent or machine is reading it. Because the memory is ordinary Markdown, it remains auditable and portable, and git tracks its history.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.