Skip to content

officialerictm/LEO7

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Leonardo AI Universal (LEO7)

    __    _______  ____     _   _____    ____  ____   ____ 
   / /   / ____/ / __ \   / | / /   |  / __ \/ __ \ / __ \
  / /   / __/   / / / /  /  |/ / /| | / /_/ / / / // / / /
 / /___/ /___  / /_/ /  / /|  / ___ |/ _, _/ /_/ // /_/ / 
/_____/_____/  \____/  /_/ |_/_/  |_/_/ |_/_____/ \____/  
                                                          
         AI Universal - Deploy Anywhere, Run Everywhere

License: MIT Version Platform

🌟 What is Leonardo AI Universal?

Leonardo AI Universal (LEO7) is a revolutionary cross-platform solution that transforms any USB drive into a portable, secure AI environment. With a single seed file, you can deploy AI models to USB drives, local systems, containers, cloud instances, and air-gapped environments - all without leaving a trace on host systems.

✨ Key Features

  • 🔒 Zero-Trace Security: Paranoid by design, leaves no footprint on host systems
  • 🌍 Universal Compatibility: One USB works on any computer (Mac, Windows, Linux)
  • 🧠 Adaptive Intelligence: Automatically selects optimal models based on hardware
  • 💻 Hacker-Friendly UX: Nostalgic terminal aesthetics with modern usability
  • 🔌 Air-Gap Ready: Full offline capability for security-critical environments
  • 🚀 Multiple Deployment Targets: USB, local, container, cloud, and air-gapped
  • 📦 Modular Architecture: Hot-swappable components with assembly system
  • 🎨 Progressive UI: From beautiful CLI to full web dashboard

🚀 Quick Start

# Clone the repository
git clone https://github.com/officialerictm/LEO7.git
cd LEO7

# Run the installer
./leonardo.sh


# Follow the interactive setup!

Navigating the Menus

The installer uses a colorful text menu. Use the arrow keys or press a number to choose an option. The recommended item is always listed first so you can simply press Enter to accept it. Set LEONARDO_DEBUG=true if you need verbose output for troubleshooting.

Formatting a USB Drive

Before installing Leonardo on a USB drive you can format it on any platform:

# Linux
./leonardo.sh usb format /dev/sdX --format exfat --label LEONARDO

# macOS
diskutil eraseDisk ExFAT LEONARDO /dev/diskN

# Windows (run in PowerShell)
leonardo usb format 1 --format exfat --label LEONARDO

The Linux formatter now marks the partition as msftdata, ensuring the drive mounts correctly on macOS and Windows.

📋 Requirements

Minimum System Requirements

  • OS: Linux, macOS 10.15+, Windows 10+
  • RAM: 8GB (16GB+ recommended)
  • Storage: 500MB for Leonardo + model sizes
  • USB: 16GB+ USB 3.0 drive (for USB deployment)

Supported Models

  • Meta LLaMA 3 (8B, 70B)
  • Mistral 7B
  • Mixtral 8x7B
  • Google Gemma (2B, 7B)
  • Custom GGUF models

🏗️ Architecture

Leonardo uses a sophisticated modular architecture:

LEO7/
├── assembly/          # Build system and manifest
├── src/
│   ├── core/         # Core engine and utilities
│   ├── modules/      # Deployment modules
│   ├── ui/          # User interface components
│   └── models/      # Model management
├── tests/           # Test suite
├── docs/            # Documentation
└── examples/        # Example configurations

🤝 Contributing

We love contributions! Please see our Contributing Guide for details.

📄 License

Leonardo AI Universal is MIT licensed. See LICENSE for details.

🙏 Acknowledgments

Built with ❤️ by Eric and the amazing AI assistant team. Special thanks to the open-source community and all contributors who made this project possible.

🔗 Links


Remember: With great portability comes great responsibility. Use Leonardo wisely!

About

Leonardo AI Universal - Portable AI deployment system for USB drives and beyond

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages