Open Specification
Memory for
AI agents
that actually works.
A structured workspace for language models. Markdown files, frontmatter metadata, and a directory convention any LLM can read, write, and reason about.
// 01 — What
Not a framework.
A convention.
Brain Protocol defines how an AI agent's memory should be organized on disk. No databases, no vector stores, no proprietary formats. Just directories and markdown.
A brain is a git repository. Everything the agent knows — about people, projects, tasks, history — lives in structured markdown files with frontmatter metadata. The agent reads them on boot, writes during sessions, commits the diff.
Plain text only
Every piece of memory is a readable markdown file. Open it in any editor, grep it, version it.
Git is the database
Memory has history. Diff two sessions, revert a bad decision, audit what the agent changed.
Structured metadata
Frontmatter provides machine-readable context: type, tags, relationships, timestamps.
LLM-agnostic
Works with Claude, Gemini, GPT, Mistral — any model that can read a directory.
// 02 — Structure
The directory layout.
// 03 — Compatibility
Works with any LLM.
If it can read a file, it speaks Brain Protocol.