EzLlama

A modern, feature-rich chat interface for Ollama with conversation storage and custom AI settings.

🚀 Features

• Dual Interface: Native Electron app + Web browser access
• Conversation Storage: Save, load, and manage chat conversations
• Custom AI Settings: Per-conversation system prompts, creativity controls, and output styles
• Real-time Streaming: Live response streaming with WebSocket support
• Model Management: Download, remove, and test Ollama models
• Cross-Platform: Works on Windows, macOS, and Linux
• Network Sharing: Share web interface across your local network

📸 Screenshots

Screenshots will be added soon

🛠️ Installation

Prerequisites

• Node.js (v16 or higher)
• Ollama installed and running

Quick Start

1. Clone the repository

   git clone https://github.com/uxmauro/ezllama.git
   cd ezllama

2. Install dependencies

   npm install

3. Start the application

   npm run dev

4. Access the interfaces

   • Electron App: Opens automatically
   • Web Interface: Visit http://localhost:3000

🎛️ Custom Settings

Each conversation supports individual settings:

• System Prompt: Custom instructions for AI behavior
• Output Style: Balanced, Creative, Precise, Casual, Professional
• Creativity (Temperature): Control response randomness (0.1-2.0)
• Context Window: Adjust memory size (1K-32K tokens)
• Response Length: Control output length
• Advanced Parameters: Top P, Top K, Repeat Penalty

📁 Project Structure

ezllama/
├── src/
│   ├── main/                 # Electron main process
│   │   ├── index.js         # Main application logic
│   │   └── conversationStorage.js  # File-based storage system
│   ├── preload/             # Electron preload scripts
│   └── renderer/            # Electron renderer (React)
├── web/                     # Web client
│   └── src/                 # React web application
├── resources/               # Application resources
└── out/                     # Build output

🔧 Development

Available Scripts

• npm run dev - Start development mode (Electron + Web server)
• npm run build - Build for production
• npm run build:win - Build for Windows
• npm run build:mac - Build for macOS
• npm run build:linux - Build for Linux

API Endpoints

The web server exposes these endpoints:

• GET /api/models - List available models
• POST /api/chat - Send chat message with custom settings
• GET /api/conversations - List saved conversations
• POST /api/conversations - Save conversation
• GET /api/conversations/:id - Load specific conversation
• DELETE /api/conversations/:id - Delete conversation

🤝 Contributing

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

Development Setup

1. Fork the repository
2. Create a feature branch: git checkout -b feature-name
3. Make your changes
4. Test thoroughly
5. Submit a pull request

📄 License

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

🙏 Acknowledgments

• Ollama for the amazing local AI platform
• Electron for cross-platform desktop apps
• React for the user interface
• Socket.IO for real-time communication

📞 Support

• Issues: GitHub Issues
• Discussions: GitHub Discussions

🗺️ Future Ideas

• Dark/Light theme toggle
• Export conversations to different formats
• Voice input/output
• Multi-language support

Have an idea? Open an issue and let us know!

---