repomind

English | 中文

AI-powered Git repository intelligence in your terminal. Scan any repo and get instant insights about code health, architecture, dependencies, and risks — all in seconds.

✨ Features

• 🔍 Code Health Analysis — Complexity metrics, code smells, duplications
• 🏗️ Architecture Detection — Auto-detect project structure, patterns, and tech stack
• 📊 Dependency Audit — Track dependencies, flag outdated/vulnerable packages
• 🤖 AI Summary — Generate intelligent project summaries and README drafts
• 🚨 Risk Detection — Find hardcoded secrets, security anti-patterns, and more
• 📋 Beautiful Reports — Rich terminal output + exportable Markdown/JSON
• ⚡ Blazing Fast — Written in Python, zero heavy dependencies, works on any repo size
• 🔌 Extensible — Plugin system for custom analyzers and formatters

🚀 Quick Start

# Install
pip install repomind

# Analyze current directory
repomind analyze .

# Analyze a remote repo
repomind analyze https://github.com/user/repo

# Generate a full report
repomind report . --output report.md

# Check for secrets and risks
repomind audit . --severity high

📸 Screenshots

$ repomind analyze .

  ╔══════════════════════════════════════════════════════╗
  ║                  🧠 RepoMind v0.1.0                  ║
  ║         AI-Powered Repository Intelligence          ║
  ╚══════════════════════════════════════════════════════╝

  📁 Analyzing: my-project
  ├─ 📝 Files: 1,247
  ├─ 📝 Lines of Code: 89,432
  ├─ 🗂️ Languages: Python (72%), TypeScript (18%), Shell (7%), Other (3%)
  ├─ 🔧 Tech Stack: FastAPI, React, PostgreSQL, Redis, Docker
  └─ 📦 Dependencies: 142 (23 ⚠️ outdated, 2 🔴 vulnerable)

  🏥 Health Score: 78/100
  ├─ ✅ Complexity: Good (avg cyclomatic: 4.2)
  ├─ ⚠️ Duplication: 12.3% (3 files > 50% duplicated)
  ├─ ✅ Test Coverage: 67% (target: 80%)
  └─ ✅ Documentation: README found, 3/5 modules documented

  🚨 Security Issues: 3 found
  ├─ 🔴 HIGH: Hardcoded API key in src/config.py:42
  ├─ 🟡 MEDIUM: SQL injection risk in src/db/query.py:118
  └─ 🟡 MEDIUM: Outdated PyYAML (6.0 → 6.0.1 CVE-2020-14343)

  💡 AI Summary:
  This is a full-stack web application using FastAPI backend with React frontend.
  The project follows a clean MVC architecture but lacks comprehensive tests.
  Consider adding integration tests and updating vulnerable dependencies.

  ⏱️ Analysis completed in 2.3s

🛠️ Installation

From PyPI (Recommended)

pip install repomind

From Source

git clone https://github.com/ApacheWang/repomind.git
cd repomind
pip install -e .

📖 Usage

Analyze a Repository

# Current directory
repomind analyze .

# Specific path
repomind analyze /path/to/repo

# Remote repository (auto-clones to temp)
repomind analyze https://github.com/user/repo

Generate Full Report

# Markdown report
repomind report . --format markdown --output report.md

# JSON report (for CI/CD integration)
repomind report . --format json --output report.json

Security Audit

# All issues
repomind audit .

# Only high severity
repomind audit . --severity high

# Include dependency vulnerabilities
repomind audit . --include-deps

AI-Powered Features (requires API key)

# Set your OpenAI API key
export REPO_MIND_API_KEY=sk-xxx

# Generate AI project summary
repomind ai summary .

# Generate README draft
repomind ai readme .

# Explain a specific file
repomind ai explain src/core/engine.py

🔌 Plugins

Create custom analyzers with a simple plugin interface:

# my_plugin.py
from repomind.plugin import AnalyzerPlugin

class MyAnalyzer(AnalyzerPlugin):
    name = "my-analyzer"
    description = "My custom analyzer"

    def analyze(self, repo_path: str) -> dict:
        # Your analysis logic
        return {"metric": "value"}

    def format_result(self, result: dict) -> str:
        return f"Custom result: {result}"

🎯 Why RepoMind?

Feature	RepoMind	Other Tools
No account required	✅	❌ (SonarQube, CodeClimate)
Works offline	✅	❌
Zero config	✅	❌
AI-powered insights	✅	Limited
< 1 second setup	✅	❌
Open source & free	✅	$$$

🤝 Contributing

Contributions are welcome! Please read our Contributing Guide first.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Inspired by cloc, radare2, and SonarQube
• Built with Click and Rich

---

Made with ❤️ by ApacheWang
⭐ If you find this useful, please give it a star!