{"repo":"Brain0-ai/brain0","free":true,"listed":false,"github":"https://github.com/Brain0-ai/brain0","clone":"git clone https://github.com/Brain0-ai/brain0.git","description":"The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.","language":"Rust","stars":371,"topics":["ai","ai-agents","attestation","audit","claude","cli","code-review","coding-agents","developer-tools","dlp"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"The black box for AI-written code. git tells you what changed. brain0 tells you why : which prompt wrote it, what the agent read to write it, and whether you can trust it. Quickstart · What it answers · Give your agent memory · How it works · Comparison · Docs --- Coding agents now write most of the diff: continuously, in parallel, and opaquely. brain0 passively builds a decision graph of your repository: every commit linked to the agent intents behind it, down to the single function , with dated history, drift detection, a DLP audit of what agents read , and a two-dimensional risk score rendered green → red. No hooks, no agent cooperation, no code changes: it reads git and the transcripts your agents already write to disk. Dogfooded from day one: brain0's own development is tracked by brain0. Quickstart That's it. From any repo, up infers the repo id from your git remote, indexes the git history (the facts ), passively ingests your coding-agent sessions (the intents , with Codex and Claude Code auto-discovered), and opens the GUI at http://localhost:8787 : an explorable graph of your codebase, from repo to module, file and symbol, where clicking a commit reveals the prompts behind it, per-file diffs, and risk at a glance. Then make it a habit: What you need The only hard requirement is Node.js ≥ 20 . brain0 is offline-first: with nothing else installed it still works end to end: deterministic summaries, local feature-hash embeddings, zero egress. Local models make it better ","default_branch":null,"files":null,"tree":[],"storefront":"/r/Brain0-ai","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Brain0-ai/brain0/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}