Menu

Tree [bb140c] main /
 History

HTTPS access


File Date Author Commit
 .github 2024-11-29 Loïc Carrère Loïc Carrère [03b8e2] Updated unit tests and CI configuration (#43)
 LM-Kit-Maestro 2025-02-09 Loïc Carrère Loïc Carrère [0617c2] Slow UI regression fix (#108)
 tests 2025-01-22 Loïc Carrère Loïc Carrère [08b51b] Legacy models management (#103)
 .gitignore 2024-11-24 BeepBeepBopBop BeepBeepBopBop [ea0c6c] Editing launchsettings config, tweaking icon fo...
 LICENSE.txt 2024-11-22 Loïc Carrère Loïc Carrère [8d72ec] Initial commit
 LM-Kit-Maestro.sln 2024-11-22 Loïc Carrère Loïc Carrère [8d72ec] Initial commit
 README.md 2025-02-09 Loïc Carrère Loïc Carrère [bb140c] Update README.md (#109)
 demo.gif 2024-11-22 Loïc Carrère Loïc Carrère [8d72ec] Initial commit

Read Me

LM-Kit Maestro 🤖

Maestro is a powerful desktop application that empowers you to orchestrate AI agents directly on your local machine—completely offline. Built on the robust LM-Kit.NET, Maestro offers a modern, clean UI paired with cutting-edge generative AI features, enabling you to create personalized chatbots and conversational agents with ease.

LM-Kit Maestro


Key Features

  • Offline Operation
    Run large language models (LLMs) entirely on your laptop—no internet connection required. Your data stays secure with no external requests or data transfers.

  • Performance Evaluation
    Get a performance score for each model based on your hardware capacity, ensuring optimal resource usage.

  • Conversational Agent Creation
    Easily create tailored conversational agents to suit your personal or professional needs. Maintain conversation history and seamlessly switch between different models within the same discussion.

  • Predefined AI Agents
    Utilize a collection of predefined AI agents for tasks such as text correction, translation, tone adjustment, and more.

  • Flexible Model Integration
    Choose from a curated list of the best models on the market or integrate custom models to meet your specific requirements.

  • Customizable Sampling Configuration
    Adjust sampling parameters to prioritize creativity or determinism in AI responses.

  • Response Evaluation and Regeneration
    Evaluate the quality of AI responses and regenerate them using different parameters to refine outputs.

  • Robust Orchestration with LM-Kit.NET
    Benefit from the most complete AI agent orchestration system for .NET, ensuring reliability and performance.


Technical Specifications

  • Open Source & Free
    Maestro is available free for both personal and professional use, licensed under the MIT License.

  • Built with .NET MAUI & Razor
    Developed using .NET MAUI with Razor, ensuring a modern, cross-platform experience.

  • Cross-Platform Compatibility
    Optimized to run on any device—even without a GPU—and compatible with both Windows and macOS.

  • Continuous Improvement
    Maestro is under active development, with frequent updates and new features on the horizon.


Coming Soon

  • RAG Support – Enhance retrieval-augmented generation capabilities.
  • Vision Support – Integrate image processing and computer vision features.
  • Audio Support – Add capabilities for audio processing and speech recognition.
  • Automation Tools – Simplify complex workflows with advanced automation features.
  • Structured Content Generation – Generate structured and formatted content.
  • Mobile Support – Extend Maestro’s powerful features to mobile platforms.

Get Started

Explore the source code, contribute, or simply get started with Maestro by visiting our GitHub repository.

Maestro brings the power of generative AI to your desktop, providing a secure, flexible, and user-friendly environment for creating and managing AI agents. Experience the future of on-device AI today!

Roadmap

You can see the full roadmap here

License

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

Contributing

Contributions from the community are welcome !

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.