A comprehensive user interface for interacting with Llama Stack API endpoints.
- Chat Interface: Interact with Llama models through a user-friendly chat interface
- Agent Management: Create, configure, and manage AI agents
- Tool Integration: Explore and test available tools with the Llama models
- Model Management: View and manage available Llama models
- Settings: Configure your Llama Stack UI preferences and connections
Comprehensive documentation is available in the documentation directory:
- Getting Started - Installation guides for different platforms
- User Documentation - Guides for end users
- Developer Documentation - Information for developers
- Feature Guides - Detailed guides for specific features
For a quick overview of the project, see the Documentation Home.
- Frontend: React with TypeScript, Material-UI
- Backend: Express.js server that proxies requests to the Llama Stack API
For detailed installation instructions, please refer to our OS-specific guides:
- Node.js (v16 or higher)
- npm (v7 or higher)
- Llama Stack API server running
- Clone the repository
- Install dependencies:
# Install server dependencies
cd server && npm install
# Install client dependencies
cd ../client && npm install-
Configure environment variables:
- Create a
.envfile in the server directory - Add the necessary configuration (see Configuration section below)
- Create a
-
Start the development server:
# Start server
cd server && npm run dev
# Start client (in a new terminal)
cd client && npm startThis will start both the Express server and the React development server.
- Express server: http://localhost:3001 (or the port specified in your .env)
- React development server: http://localhost:3000
- Open your browser and navigate to http://localhost:3000
- Use the sidebar to navigate between different features
- Start by exploring the available agents and tools
- Try the chat interface to interact with your configured agents
For detailed usage instructions, please refer to the User Guide.
PORT: The port on which the Express server will run (default: 3001)LLAMA_API_URL: The URL of the Llama API server (default: http://localhost:8000)NODE_ENV: The environment in which the server is running (development, production)
The client configuration is managed through the server. No separate .env file is needed for the client in development mode.
You can also configure the Llama API URL in the Settings page of the application.
For more detailed configuration options, please refer to the Developer Guide.
This project is licensed under the ISC License.
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
For more information on how to contribute, please refer to the Developer Guide.