Sigma Eclipse LLM

Run powerful AI locally — no cloud, no limits, complete privacy.

Features • Installation • How It Works • Development • License

---

This application is a core component of the Sigma Eclipse project — a privacy-focused AI ecosystem. It works seamlessly with:

• Sigma Browser — A privacy-first browser with built-in AI capabilities
• Sigma Eclipse Extension — Browser extension that connects to this local LLM server

Together, these components provide a complete solution for running AI locally while browsing the web, ensuring your data stays on your machine.

Sigma Eclipse LLM is a lightweight desktop application that lets you run large language models (LLMs) locally on your machine. No API keys, no subscriptions, no data leaving your computer — just pure, private AI at your fingertips.

Built with Tauri and powered by llama.cpp, Sigma Eclipse LLM combines native performance with a beautiful, intuitive interface.

• One-click setup — automatically downloads everything you need
• Zero configuration — smart defaults that just work
• Clean interface — no clutter, no confusion

• 100% local — your data never leaves your machine
• No accounts — no sign-ups, no tracking, no telemetry
• Offline capable — works without internet after initial setup

• GPU acceleration — automatic GPU detection and optimization
• Multiple models — switch between models easily
• Native performance — Rust backend with minimal resource usage
• Browser integration — seamless connection with Sigma browser extension

• macOS (Apple Silicon)
• Windows (x64)

Download the latest release for your platform:

1. Open Sigma Eclipse
2. Wait for automatic setup — the app downloads llama.cpp and the default model (~3-6 GB)
3. Click "Start" — your local AI server is now running!

That's it. No terminal commands, no manual downloads, no config files.

┌─────────────────────────────────────────────────────────────┐
│                     Sigma Eclipse                            │
│                                                              │
│  ┌──────────────┐    ┌──────────────┐    ┌──────────────┐   │
│  │   React UI   │◄──►│  Tauri Core  │◄──►│  llama.cpp   │   │
│  │  (Frontend)  │    │    (Rust)    │    │   (Server)   │   │
│  └──────────────┘    └──────────────┘    └──────────────┘   │
│                              │                               │
│                              ▼                               │
│                   ┌──────────────────┐                      │
│                   │  Native Messaging │                      │
│                   │   (Browser API)   │                      │
│                   └──────────────────┘                      │
└─────────────────────────────────────────────────────────────┘

Sigma Eclipse manages a local llama.cpp server that provides an OpenAI-compatible API. This means:

• 🌐 Local API endpoint at http://localhost:8080
• 🔌 Compatible with any tool that supports OpenAI API
• 🧩 Native messaging enables browser extensions to communicate directly

Access settings via the ⚙️ gear icon:

💡 Tip: Sigma Eclipse automatically detects your hardware and suggests optimal settings.

• Node.js v18+
• Rust (latest stable)
• Platform-specific dependencies:
  • macOS: xcode-select --install
  • Windows: Visual Studio C++ Build Tools

# Clone the repository
git clone https://github.com/ai-swat/sigma-eclipse-llm.git
cd sigma-eclipse-llm

# Install dependencies
npm install

# Run in development mode
npm run tauri dev

npm run tauri build

Built artifacts will be in src-tauri/target/release/bundle/

sigma-eclipse-llm/
├── src/                    # React frontend
│   ├── components/         # UI components
│   ├── hooks/              # React hooks
│   ├── styles/             # CSS styles
│   └── types/              # TypeScript types
├── src-tauri/              # Rust backend
│   ├── src/
│   │   ├── main.rs         # Entry point
│   │   ├── server.rs       # LLM server management
│   │   ├── download/       # Model & binary downloads
│   │   └── native_messaging.rs
│   └── tauri.conf.json     # Tauri configuration
└── package.json

Contributions are welcome! Please feel free to submit a Pull Request.

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

This project is licensed under the PolyForm Noncommercial License 1.0.0.

TL;DR: Free for personal, educational, and non-commercial use. Contact us for commercial licensing.

• llama.cpp — The amazing LLM inference engine
• Tauri — Framework for building tiny, fast desktop apps
• Hugging Face — Model hosting and community