Skip to content

Understand Any Repo in seconds. Instantly generate AI-ready code digests, visualize repository structures, and chat with your codebase using Git Scape AI.

License

Notifications You must be signed in to change notification settings

jmxt3/Git-Scape-Web

Repository files navigation

Git Scape AI

Understand any GitHub repository in seconds.

React Google Cloud Gemini Docker


🚀 Overview

GitScape

Git Scape AI is an open-source tool that instantly generates AI-ready text digests of GitHub codebases, visualizes repository structures with interactive diagrams, and enables contextual AI-powered chat to help you understand, debug, and refactor code. It supports both public and private repositories.

  • AI Code Summaries: Get concise, AI-generated summaries of any GitHub repo.
  • Interactive Visualizations: Explore your codebase structure with beautiful, interactive diagrams.
  • AI Chat with Code: Ask questions about your codebase and get instant, context-aware answers.
  • Privacy First: All API keys are stored securely in your browser.
  • Backend API: Integrate with the official Git Scape API for advanced repository analysis and automation.

🏁 Quick Start

Prerequisites

1. Clone the Repository

git clone https://github.com/your-username/git-scape-ai.git
cd git-scape-ai

2. Install Dependencies

npm install

3. Set Up API Keys

  • Gemini API Key:
    • Get your Gemini API Key.
    • Create a .env.local file in the project root:
      GEMINI_API_KEY=your-gemini-api-key-here
  • GitHub Personal Access Token (PAT):

4. Run the App

npm run dev

Visit http://localhost:5173 in your browser.


🐳 Docker Deployment

You can build and run the app in a Docker container, suitable for deployment to Google Cloud Run or any container platform.

1. Build the Docker Image

docker build -t git_scape_web .

2. Run the Docker Container Locally

docker run -d -p 8080:8080 --name git_scape_web_local git_scape_web

Then visit http://localhost:8080 in your browser.


🧑‍💻 Contributing

We welcome contributions of all kinds! Here’s how to get started:

  1. Fork the repository and create your branch:
    git checkout -b feature/your-feature-name
  2. Make your changes (see Project Structure).
  3. Test locally (npm run dev).
  4. Commit and push your changes.
  5. Open a Pull Request with a clear description.

Code Style


🗂️ Project Structure

├── App.tsx                # Main app logic
├── components/            # All React components
├── services/              # API and utility services
├── types.ts               # TypeScript types
├── constants.ts           # App-wide constants
├── index.html             # HTML entry point
├── vite.config.ts         # Vite config
├── ...
  • components/: UI and feature components (modals, diagrams, chat, etc.)
  • services/: API integrations (GitHub, Gemini)
  • types.ts: Shared TypeScript types/interfaces
  • constants.ts: Centralized constants (API endpoints, keys, etc.)

🛡️ Security & Privacy

  • API keys are never sent to any server except the official Gemini or GitHub APIs.
  • No tracking: All analytics are opt-in and anonymized.
  • Open Source: Review the code, suggest improvements, or fork for your own use!

🖥️ Backend API

Looking to automate repository analysis, generate digests, or build your own integrations? Check out the official Git Scape API — a robust, open-source FastAPI backend that powers Git Scape AI. It supports:

  • RESTful endpoints for digest generation
  • Real-time progress via WebSockets
  • Easy deployment (Docker & Google Cloud Run ready)
  • Designed for scalability and security

Get started: Git Scape API on GitHub


📚 Resources


📝 License

This project is licensed under the MIT License.


🙏 Acknowledgements

Created by João Machete and contributors.

If you like this project, please ⭐️ the repo and share your feedback!

About

Understand Any Repo in seconds. Instantly generate AI-ready code digests, visualize repository structures, and chat with your codebase using Git Scape AI.

Topics

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages