# study8677/repobrain

🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.

Repository: https://github.com/study8677/repobrain
Canonical: https://ross.abutalabs.com/products/repobrain
Homepage: https://deepwiki.com/study8677/antigravity-workspace-template
Language: Python
License: MIT
License Family: permissive
Topics: claude-code, codex-cli, developer-tools, mcp-server, windsurf, code-search, rag, agents-sdk, ai-agent, code-intelligence, codebase-qa, copilot, cursor, ide-plugin, knowledge-graph, llm, mcp, multi-agent, openai, python
Last push: 2026-08-26T07:44:33+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 80, longevity 20
- inputs: {"age_days": 287, "days_push": 7, "days_rel": 54, "gap_med": 35.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1320, forks 265 (observed 2026-08-28T04:04:21.734387+00:00)

## What it is
RepoBrain (formerly Antigravity) is an MCP server and AI coding assistant plugin that indexes a codebase into a knowledge base so you can ask grounded questions about it with file paths and line numbers. It works across Claude Code, Cursor, Codex, Windsurf, Gemini CLI, VS Code Copilot, Cline, and Aider.

## Use cases
- ask questions about my codebase with answers grounded in real code
- index a repository so AI coding assistants understand it
- set up an MCP server for codebase Q&A in Claude Code
- find how authentication works in this repo
- give Cursor or Windsurf deep context about my project
- build a knowledge graph of my codebase for LLM agents

## When to choose
- you use Claude Code, Cursor, Codex, Windsurf, or similar AI coding tools and want codebase-aware answers
- you need grounded code Q&A with file paths and line numbers instead of hallucinated explanations
- you want an MCP server that indexes your repo once and serves many AI clients

## When to avoid
- you need a general-purpose RAG pipeline for non-code documents
- you want a standalone chat UI rather than integration into existing AI coding tools
- your project cannot run a local Python-based indexing backend

## Facets
- artifact type: plugin
- maturity: active
- function: rag, search-engine, mcp, agent-framework, chatbot, developer-tools
- domain: developer-tools, large-language-models
- platform: python, cli, cross-platform, editor-plugin
- tags: mcp-server, claude-code, cursor, codebase-qa, knowledge-graph, code-search, multi-agent, llm, retrieval-augmented-generation, ai-agents, code-intelligence

## Member repositories
- study8677/repobrain (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:21.734387+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:47:51.795474+00:00, confidence not recorded.
  - readme: https://github.com/study8677/repobrain (fetched 2026-08-28T04:04:21.734387+00:00, sha f5e07275377b)
  - homepage: https://deepwiki.com/study8677/antigravity-workspace-template (fetched 2026-08-29T12:06:32.825159+00:00, sha af71156aeaf0)
  - site_page: https://deepwiki.com/study8677/antigravity-workspace-template/2-getting-started (fetched 2026-08-29T12:06:32.834300+00:00, sha e2a42bb5ff62)
  - site_page: https://deepwiki.com/study8677/antigravity-workspace-template/2.1-installation (fetched 2026-08-29T12:06:32.837458+00:00, sha 816ef67a02de)
- Data as of 2026-08-30T08:39:29.467469+00:00.