Skip to content

Headless Mode

"Headless Mode" refers to running Backend.AI GO primarily as a background service or server, without relying on the graphical user interface (GUI) for daily interactions. This is particularly useful for setting up a dedicated inference server on a spare machine or managing the application remotely.

Concept

Although Backend.AI GO is a desktop application, its core is decoupled:

  • Backend (Rust): Handles model inference, the API server, and the Continuum Router.
  • Frontend (React/Tauri): The visual chat interface.

You can interact with the Backend entirely through the Management API or the CLI tool, effectively treating the GUI as optional.

Operation

System Tray

The simplest form of "headless-like" operation is closing the main window. * By default, closing the window minimizes Backend.AI GO to the System Tray (Menu Bar on macOS). * The API server and model inference continue running in the background.

CLI Control

You can use the bundled backend-ai-go CLI to manage the application without opening the window.

# List loaded models
backend-ai-go model list

# Load a model
backend-ai-go model load --name "llama-3-8b-instruct"

# Check system stats
backend-ai-go system info

See the CLI Reference for full documentation.

Remote Access (Server Mode)

To turn your local machine into a headless node for others:

  1. Go to Settings > Advanced.
  2. Enable Remote Access (Allow external connections).
  3. Set the API Port (default: 8080).
  4. (Optional) Setup a firewall rule to allow traffic on that port.

Now, other instances of Backend.AI GO (or curl/Python scripts) can connect to your machine's IP address as if it were a server.

Note: True command-line-only startup (without any GUI framework initialization) is planned for future Linux server builds.