🚀 Codev

AI Pair Programming Tool for Your Terminal

Codev is an AI-powered pair programming assistant designed for developers who prefer a terminal-first workflow.
It helps developers interact with repositories, automate coding tasks, and enhance productivity directly from the command line.

---

✨ Features

• 🚀 Terminal-first workflow
• 🤖 AI-assisted pair programming
• 📦 Python package with CLI support
• 🛠️ Open source and extensible
• ⚡ Built for modern Python versions
• 🔧 Easy integration with AI providers and APIs
• 📁 Repository-aware code understanding
• 💡 Designed for developer productivity

---

📦 Installation

Install from PyPI

pip install codev

---

Install from Source

git clone https://github.com/your-username/codev.git

cd codev

pip install .

---

Install in Development Mode

git clone https://github.com/your-username/codev.git

cd codev

pip install -e .

---

🚀 Usage

Run Codev

codev

---

Run as Python Module

python -m codev

---

⚙️ Example Usage

codev --model gemini/gemini-2.5-flash

codev --help

---

📋 Requirements

• Python 3.10 or newer
• Supported terminal environment
• Git installed (recommended)
• Internet connection for cloud AI providers
• API keys for supported models/providers

---

🔑 Setting API Keys

Windows PowerShell

setx GEMINI_API_KEY "your_api_key"

---

Linux / macOS

export GEMINI_API_KEY="your_api_key"

---

🧑‍💻 Development Setup

Clone Repository

git clone https://github.com/your-username/codev.git

cd codev

---

Install Dependencies

pip install -e .

---

Run Tests

pytest

---

📤 Publishing to PyPI

Install Build Tools

pip install build twine

---

Build Package

python -m build

This generates distribution files inside:

dist/

---

Verify Package

twine check dist/*

---

Upload to PyPI

twine upload dist/*

---

📁 Project Structure

codev/
├── codev/                # Main Python package
├── pyproject.toml        # Build configuration
├── requirements.txt      # Runtime dependencies
├── LICENSE               # Project license
├── README.md             # Documentation
└── tests/                # Test files (optional)

---

🧠 Research & Vision

Codev aims to provide an intelligent software engineering experience by combining:

• AI-assisted development workflows
• Repository-aware code understanding
• Terminal productivity tooling
• Context-aware code generation
• Extensible developer infrastructure

This project can also serve as a research platform for:

• AI software engineering agents
• Context engineering for LLMs
• Autonomous code generation systems
• Multi-model orchestration
• Intelligent developer assistants

---

🛠️ Supported Use Cases

• Code generation
• Repository understanding
• Bug fixing assistance
• Developer productivity automation
• AI-assisted refactoring
• Context-aware coding workflows

---

📄 License

This project is licensed under the Apache License 2.0.

See the LICENSE file for more information.

---

🤝 Contributing

Contributions, issues, and feature requests are welcome.

Feel free to fork the repository and submit pull requests.

---

⭐ Support

If you find this project useful:

• ⭐ Star the repository
• 🍴 Fork the project
• 🛠️ Contribute improvements
• 📢 Share feedback

---

📬 Contact

For collaboration, suggestions, or research discussions, feel free to connect.

---