Alris is an automation system that converts natural language commands into actionable tasks and workflows. It exposes a backend server (FastAPI) paired with a web-based UI, and supports real-time, WebSocket-based communication for immediate feedback and control. Clients can issue natural language prompts such as 'search weather in London' or 'open github.com', and Alris will interpret these commands, perform the appropriate web actions, fetch results, and return or display them through the UI. The server provides a small, extensible command surface focused on web-based actions like web search, opening URLs, and playing media, making it suitable for automating routine information retrieval and media tasks via simple language queries. The system also supports orchestration of tasks and monitoring, enabling users to track execution status and outcomes in real-time through the client interface.

Prerequisites:

• Python 3.x installed
• Node.js 16+ (for optional client UI) and npm/yarn (optional if using prebuilt UI)
• Virtual environment (recommended for Python)

Server installation steps:

1. Navigate to the server directory: cd server
2. Create and activate a virtual environment: python -m venv myenv source myenv/bin/activate # Linux/macOS

   On Windows use: myenv\Scripts\activate

3. Install dependencies: pip install -r requirements.txt
4. Install Playwright browsers (for any browser automation features used by the server): playwright install
5. Run the server: python run.py

Client (optional) installation:

1. Navigate to the client directory: cd client
2. Install dependencies: npm install
3. Start the development server: npm run dev The client UI will typically be available at http://localhost:3000

• The server is Python-based and likely uses FastAPI with WebSocket support for real-time communication.
• If you encounter environment issues, ensure the virtual environment is activated and dependencies from requirements.txt are installed.
• When running locally, you may need to install browser automation tooling (Playwright) depending on the features used.
• The available commands currently exposed by the server are:
  • search [query] — perform a web search
  • open [url] — open a specified URL
  • play video of [query] — search and play a video
  • play music of [query] — search and play music
• For deployment, you can run the server with Python directly or containerize it if desired. Ensure network access for WebSocket communication if the client UI is hosted separately.
• If the UI and server are separated, configure the client to point to the correct server URL (including websockets endpoint) in the client configuration.