tai (Terminal AI) 🚀

A powerful CLI companion that helps you remember terminal commands, powered by Google's Gemini 2.0 Flash model.

✨ Features

• 🧠 Smart command suggestions based on natural language queries
• 🎯 Platform-specific command recommendations
• 🔄 Automatic retry with exponential backoff
• 🎨 Rich terminal output with colored feedback
• 📝 Detailed command explanations
• 📋 Clipboard integration
• ⚡ Powered by Gemini 2.0 Flash for superior speed and accuracy
• 🛡️ Graceful error handling and signal management
• 🔌 Easy to extend with modular architecture

🔧 Requirements

• Python 3.8 or higher
• GEMINI_API_KEY environment variable (get it from Google AI Studio)

📦 Installation

Using pip (global)

pwsh -Command "git clone https://github.com/ubranch/tai.git"
pwsh -Command "cd tai && pip install ."

For development:

# Clone the repository
pwsh -Command "git clone https://github.com/ubranch/tai.git"
pwsh -Command "cd tai"

# Install dependencies
pwsh -Command "uv venv --python 3.10"
pwsh -Command "uv activate"
pwsh -Command "uv pip install -r requirements.txt"

🔑 Setup

# Set your Gemini API key
pwsh -Command "$env:GEMINI_API_KEY='your_api_key_here'"

For permanent setup, add the above line to your PowerShell profile:

pwsh -Command "if (!(Test-Path -Path $PROFILE)) { New-Item -ItemType File -Path $PROFILE -Force }; Add-Content -Path $PROFILE -Value '$env:GEMINI_API_KEY=''your_api_key_here''''"

🚀 Usage

> tai "download youtube video as mp3"
yt-dlp -x --audio-format mp3 <youtube_video_url>
Downloads a YouTube video and converts it to an MP3 file using yt-dlp. Replace <youtube_video_url> with the actual URL.
Copy to clipboard? [y/n] (n): y
copied to clipboard!

📝 Version History

5.4.1

• fix: model name to use correct version identifier (gemini-2.0-flash)
• docs: update documentation to reflect correct model information

5.4.0

• feat: upgrade to Gemini 2.0 Flash model for superior speed and accuracy
• perf: optimize model parameters for better command suggestions
• feat: increase token limit for more detailed responses
• tune: fine-tune temperature and top_p settings for improved stability

5.3.0

• feat: update to use Gemini 1.5 Pro model for improved reliability
• feat: add retry mechanism with exponential backoff
• enhance: error handling and feedback
• feat: add command explanations
• improve: platform-specific command detection

🔧 Development

Project Structure

tai/
├── core/           # Core functionality
├── utils/          # Utility functions
├── cli.py          # Command-line interface
├── config.py       # Configuration management
├── prompt.md       # Prompt templates
└── __init__.py     # Package initialization

🤝 Contributing

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

Commit Convention

We follow Conventional Commits. Examples:

• feat: add new feature
• fix: resolve bug
• docs: update documentation
• style: format code
• refactor: restructure code
• test: add tests
• chore: update dependencies

📄 License

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

🙏 Acknowledgments

• Google's Gemini team for providing the powerful AI model
• The Python community for excellent libraries
• All contributors who help make this project better