study8677/repobrain

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

What it solves

RepoBrain provides a cross-IDE repository knowledge engine that prevents AI agents from hallucinating or forgetting coding styles when interacting with large codebases. It replaces the inefficient process of having an AI manually grep through files or read massive documentation files with a structured, grounded Q&A system that provides exact file paths and line numbers.

How it works

RepoBrain creates a shared knowledge layer in a .repobrain/ folder that is portable across different IDEs. It uses a multi-agent cluster to autonomously analyze the codebase:

  1. Knowledge Generation (rb-refresh): A pipeline of agents scans the codebase, groups files by import graphs and directory structure, and generates comprehensive Markdown knowledge documents for each module. A Map Agent then indexes these into a map.md file.
  2. ** uma Router-based Q&A (rb-ask)**: When a user asks a question, a Router reads the map.md index to identify the relevant modules and feeds the corresponding agent documents to answer agents, which then synthesize a grounded answer.
  3. Integration: It integrates as a plugin for Claude Code and Codex CLI, or as an MCP server for other compatible IDEs like Cursor, Windsurf, and VS Code.

Who it’s for

Developers using AI-powered IDEs and agents (such as Claude Code, Cursor, Windsurf, Codex, or Aider) who need their AI assistants to have a deep, grounded understanding of their specific project architecture and conventions.

Highlights

  • Cross-IDE Portability: One .repobrain/ folder works across multiple AI editors.
  • Language Agnostic: Uses LLM-driven analysis of directory structures and source code rather than AST parsing, making it compatible with any programming language.
  • No-API-Key Mode: Can leverage existing logged-in CLI sessions (like Claude Code or Codex) to run its engine without requiring a separate API key.
  • Grounded Answers: Provides answers backed by real code evidence, including specific file paths and line numbers.
  • Git Integration: Includes a dedicated GitAgent to analyze git history for "who, what, and why" insights.

Related

  • Project
    mxyhi/ok-skills

    A curated collection of reusable skills and playbooks for AI coding agents like Claude Code and Cursor, providing structured workflows for tasks like browser automation and codebase planning.

  • Project
    repowise-dev/repowise

    Repowise is an open‑source Python tool that builds a local, continuously‑updated index of a codebase (graph, git history, tests, docs, decisions). It exposes ten deterministic MCP endpoints that let AI coding agents and developers retrieve cited answers, change‑risk scores, test‑impact lists, and concrete refactoring plans with far fewer token calls. The system also provides a health‑score engine (49 detectors) and a GitHub PR bot that posts risk and health analysis directly on pull requests. Installation is a simple `pip install repowise`, `repowise init`, and `repowise serve`. The project is AGPL‑3.0 licensed, self‑hosted, and backed by published benchmarks showing ~30 % reduction in agent output and 97 % smaller payloads.

  • Project
    NateBJones-Projects/OB1

    An infrastructure layer that provides a single, shared persistent memory database with vector search for all your AI tools, eliminating fragmented data across different AI clients.

  • Project
    rohitg00/agentmemory

    A persistent memory server for AI coding agents that automatically captures and retrieves project context across sessions using hybrid search.

  • Project
    rohitg00/pro-workflow

    A persistent memory and knowledge plane for AI coding agents that eliminates repetitive corrections through self-correcting SQLite-backed memory and auto-growing research wikis.