← all repositories
study8677/repobrain

A ChatGPT for your repo that actually cites line numbers

Antigravity builds a multi-agent knowledge layer inside your repo so Claude, Cursor, or Codex can answer architecture questions with real file paths instead of confident hallucinations.

repobrain
Not currently ranked.
star history

What it does

Antigravity is a cross-IDE knowledge engine that indexes your codebase into a local .antigravity/ folder. A cluster of module-specific agents reads every part of your project and writes structured knowledge docs; when you ask a question via ag-ask, a router dispatches it to the agent that actually owns that code. Answers come back grounded in real source files, complete with paths and line numbers, rather than repo-wide grep dumps.

The interesting bit

The portability angle is the real architecture: it is not a plugin but a file-based knowledge layer. Because the intelligence lives in plain Markdown under .antigravity/, any IDE—Claude Code, Cursor, Codex CLI, Windsurf—can read the same context without vendor lock-in. It is essentially treating your repository as a static site and every module as its own embedded librarian.

Key highlights

  • Benchmarked (self-reported, n=36) at 99% factual accuracy on Python codebases, with 2.1× lower latency than Codex CLI on lookup questions.
  • Each module gets its own agent during ag-refresh, producing a distributed knowledge graph rather than one monolithic context blob.
  • Ships as slash commands inside Claude Code and Codex CLI, plus a standalone CLI and MCP server.
  • Supports any OpenAI-compatible endpoint, including local Ollama.
  • Offers a “context files only” mode that bootstraps IDE entry files without requiring an LLM.

Caveats

  • Synthesis and high-level architecture questions scored 81% in the project’s own benchmark, well behind Codex CLI (100%) and Claude Code (94%).
  • Requires an upfront ag-refresh build step that can take minutes; stale knowledge bases produce stale answers.
  • Codex CLI support currently needs a manual engine install because Codex hooks are not yet supported.

Verdict

Worth a look if you juggle multiple AI IDEs and want a single, portable knowledge layer that beats raw agents on factual lookups. Skip it if your primary need is high-level architectural synthesis, where native Codex or Claude still outperform.

Frequently asked

What is study8677/repobrain?
Antigravity builds a multi-agent knowledge layer inside your repo so Claude, Cursor, or Codex can answer architecture questions with real file paths instead of confident hallucinations.
Is repobrain open source?
Yes — study8677/repobrain is open source, released under the MIT license.
What language is repobrain written in?
study8677/repobrain is primarily written in Python.
How popular is repobrain?
study8677/repobrain has 1.4k stars on GitHub.
Where can I find repobrain?
study8677/repobrain is on GitHub at https://github.com/study8677/repobrain.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.