What it does
This project contains two AI agent tools. UI-TARS Desktop is a desktop app that lets an AI model look at your screen and control the mouse and keyboard, on your own computer or a remote one, and in a web browser.
Agent TARS is a related tool that runs from the terminal or in a web page. It uses AI models that understand both pictures and text, and can connect to outside tools. An example in the README asks it to book flights on a travel website.
You need to connect it to an AI model, either one you run yourself or an online service with an account key.
Who it's for
Tech-curious users and developers who want to try AI that operates a computer for them.
Can I use it without coding?
With some setup. The desktop app needs an AI model to be set up. Agent TARS installs with a command and needs Node.js. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
- Install Node.js version 22 or newer on your computer.
- Start Agent TARS from the terminal, giving it your AI provider, model and API key.
- Describe a task, such as booking a hotel, and watch it work in the browser.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- More on staying safe