repobrain

RepoBrain

Give your repo a brain 🧠 — ChatGPT for your codebase, works in Claude Code, Cursor, Codex, Windsurf & 4 more.

Formerly known as Antigravity Workspace Template — same project, new name.

English · 中文 · Español

# 1 — Install (Claude Code plugin marketplace)
/plugin marketplace add study8677/repobrain
/plugin install repobrain@repobrain

# 2 — Configure a backend (logged-in local CLI = no key, or paste an API key), build the knowledge base
/repobrain:rb-setup
/repobrain:rb-refresh

# 3 — Ask anything, grounded in real code with file paths + line numbers
/repobrain:rb-ask "How does auth work?"

95.83% weighted semantic accuracy · 4.04× faster scored queries than CodeGraph + Trae on the main track. Benchmark results ↓ Codex CLI users — drop the repobrain: prefix; the same four slash commands ship there too.

🧠 Fastest start — let your AI install it for you (no API key)

Already in a logged-in AI IDE (Trae / Cursor / Claude Code / Codex)? Don't touch pip or an API key — paste this one line to your AI assistant and it does the rest (detects your logged-in CLI, wires up a zero-key backend, initializes the project, self-tests):

Read https://github.com/study8677/repobrain/blob/main/AI_INSTALL.md and follow it to install RepoBrain in this project.

Then just ask your AI anything about your codebase.

---

Why RepoBrain?

Cross-IDE repository knowledge engine for grounded codebase Q&A. Same .repobrain/ knowledge layer reads in every IDE; one engine, every host.

An AI Agent's capability ceiling = the quality of context it can read.

rb-refresh deploys a multi-agent cluster that autonomously reads your code — each module gets its own Agent that generates a knowledge doc. rb-ask routes questions to the right Agent, grounded in real code with file paths and line numbers.

Instead of handing Claude Code / Codex a repo-wide grep and making it hunt on its own, give it a ChatGPT for your repository.

Traditional approach:              RepoBrain approach:
  CLAUDE.md = 5000 lines of docs     Claude Code calls ask_project("how does auth work?")
  Agent reads it all, forgets most   Router → ModuleAgent reads actual source, returns exact answer
  Hallucination rate stays high      Grounded in real code, file paths, and git history

Problem	Without RepoBrain	With RepoBrain
Agent forgets coding style	Repeats the same corrections	Reads .repobrain/conventions.md — gets it right the first time
Onboarding a new codebase	Agent guesses at architecture	rb-refresh → ModuleAgents self-learn each module
Switching between IDEs	Different rules everywhere	One .repobrain/ folder — every IDE reads it
Asking "how does X work?"	Agent reads random files	ask_project MCP → Router routes to the responsible ModuleAgent

Architecture is files + a live Q&A engine, not plugins. Portable across any IDE, any LLM, zero vendor lock-in.

---

RepoBrain vs CodeGraph + Trae (2026-09-09)

Flask, ripgrep, Vite, Prometheus · 20 questions × 3 repeats per product · same source access and model route (Seed-2.1-Turbo → seed-code-pro).

Main-track metric	RepoBrain	CodeGraph + Trae
Weighted semantic accuracy	95.83%	84.17%
Successful queries	60/60	53/60
Scored query time	5,106.67 s	20,621.14 s
Query tokens	22,326,315	86,027,974
Cold build time	7,420.63 s	9.58 s
Cold build + scored queries	12,527.30 s	20,630.72 s

Failures count as incorrect. Cold builds compare full AI knowledge generation with static code-graph indexing, not equivalent workloads. Results apply to this locked experiment only.

Full results and methodology

---

Quick Start

Plugin install for Claude Code / Codex CLI (recommended — the rb CLI and engine auto-install together on Claude's first session):

# Claude Code
/plugin marketplace add study8677/repobrain
/plugin install repobrain@repobrain
/repobrain:rb-setup            # interactive: use a logged-in local CLI (Codex/Trae/Claude, no key) or paste an API key; writes .env
/repobrain:rb-refresh          # first refresh auto-creates .repobrain/
/repobrain:rb-ask "How does this project work?"

# Codex CLI (manual engine install — Codex hooks are not yet supported)
pipx install "git+https://github.com/study8677/repobrain.git#subdirectory=engine"
pipx inject --force --include-apps repobrain-engine "git+https://github.com/study8677/repobrain.git#subdirectory=cli"
codex plugin marketplace add study8677/repobrain
/rb-setup
/rb-refresh
/rb-ask "How does this project work?"

Codex auto-discovers slash commands from the plugin's commands/ directory, so the same four commands work without the repobrain: namespace prefix. The raw CLI calls (rb-refresh --workspace ., rb-ask "..." --workspace .) also still work. If your Codex build supports MCP, register rb-mcp --workspace <project> separately.

# 1. Install engine + CLI
pip install "git+https://github.com/study8677/repobrain.git#subdirectory=cli"
pip install "git+https://github.com/study8677/repobrain.git#subdirectory=engine"

# 2. Configure .env with any OpenAI-compatible API key
cd my-project
cat > .env <<EOF
OPENAI_BASE_URL=https://your-endpoint/v1
OPENAI_API_KEY=your-key
OPENAI_MODEL=your-model
RB_ASK_TIMEOUT_SECONDS=120
EOF

# 3. Build knowledge base (ModuleAgents self-learn each module)
rb-refresh --workspace .

# 4. Ask anything
rb-ask "How does auth work in this project?"

# 5. (Optional) Register as MCP server for Claude Code
claude mcp add repobrain rb-mcp -- --workspace $(pwd)

pip install git+https://github.com/study8677/repobrain.git#subdirectory=cli
rb init my-project && cd my-project
# IDE entry files bootstrap into AGENTS.md; dynamic knowledge is in .repobrain/

See INSTALL.md for full install details, verification commands such as rb doctor, and troubleshooting notes for PATH, MCP, and host-specific plugin behavior.

---

Slash Commands

Same four slash commands ship to both Claude Code and Codex CLI. Claude namespaces them as /repobrain:<name>; Codex auto-discovers commands/ and surfaces the bare /<name> form. No retraining — same flow on both hosts.

Claude Code	Codex CLI	Purpose
/repobrain:rb-setup	/rb-setup	First-time setup — pick LLM provider, write .env
/repobrain:rb-refresh [quick]	/rb-refresh [quick]	Build a full baseline or manually update only affected Agent groups
/repobrain:rb-ask <question>	/rb-ask <question>	Routed Q&A on the current codebase
/repobrain:rb-init <name>	/rb-init <name>	Scaffold a new multi-agent repo from this template

A typical first session is rb-setup → rb-refresh → rb-ask. If installation or provider setup looks wrong, run rb doctor --workspace ..

rb-setup — first-time configuration

Run this once per project, right after installing the plugin. Interactive picker that first detects the headless CLIs you're already logged into (Codex / Trae / Claude / Gemini) and offers a no-API-key local host-runner as the most convenient option — no key to paste, RepoBrain just drives your existing CLI login for both rb-ask and rb-refresh. If you'd rather use a hosted model, it also offers the API-key providers (OpenAI / DeepSeek / Groq / 阿里灵积 / NVIDIA NIM / Ollama local / any OpenAI-compatible endpoint). Either way it writes .env to the project root — RB_HOST_RUNNER + RB_HOST_COMMAND for a local CLI, or OPENAI_BASE_URL / OPENAI_API_KEY / OPENAI_MODEL for a provider — and ensures .env is in .gitignore. Skip it if you already have a working .env.

rb-refresh — build / refresh the knowledge base

Deploys the multi-agent cluster and creates an atomic generation baseline. The first run must be a full refresh. Later, quick compares committed changes from the active generation to HEAD, requires a clean worktree, and lets RepoBrain's ImpactPlanner plus an independent Verifier execute only affected Agent groups. It never falls back to a full refresh. Use failed-only to resume failed or pending groups for the same target commit. rb-ask only warns about new commits; it never refreshes knowledge automatically.

Time: a few minutes for small repos, longer for large ones. Requires rb-setup to have completed. Works with either backend: an API-key/OpenAI-compatible provider runs the full LLM refresh, while a local host-runner (Codex / Trae / Claude / …) runs the tool-free stages (module docs, map.md) through your logged-in CLI and automatically degrades the tool/handoff stages (conventions, git insights) to deterministic output — no API key needed. Add RB_REFRESH_SCAN_ONLY=1 only if you want a fast structure-only index with no LLM narration at all.

rb-ask — routed Q&A on the codebase