Setup Wizard

Configure your autonomous AI agent.

Run the setup wizard to connect Tars to your Google and Discord accounts:

tars setup

The wizard will guide you through the following steps:

1. Google Authentication

Tars uses the Gemini Core engine for intelligence. The wizard will open a browser window for you to sign in with your Google account. This grants Tars direct access to Gemini models via the official Node.js Core library.

2. Communication Channel

Tars uses Discord as its communication interface.

Go to the Discord Developer Portal.
Create a new application, add a Bot, and copy the Token.
Enable the Message Content Intent under the Bot settings.

3. Model & Heartbeat

Choose your preferred Gemini model (e.g., gemini-2.0-flash) and set the Heartbeat Interval. The heartbeat is how often Tars checks for scheduled tasks or performs autonomous system checks.

4. Initialization

Tars will provision its workspace at ~/.tars/. This directory stores its memory, task list, and configuration.

Tip: If you are migrating from another machine, run tars import <path> before starting tars setup to restore your existing memory and tasks.

Lifecycle Commands

Start the agent:

tars start

Stop the agent:

tars stop

Once running, your bot will appear online in Discord. Type $ping to confirm it responded efficiently.