UI-TARS-desktop
UI-TARS-desktop is a desktop app that controls your computer and browser for you, clicking and typing through screens to finish tasks.
What it is good for
- Automating repetitive clicks and typing on your computer
- Changing settings in desktop apps without navigating menus
- Operating a browser to complete multi-step web tasks
- Controlling a remote computer or browser from another device
At a glance
- Who it is for
- Setup
- Install a desktop app or browser extension
Level 3 of 5. Download and install it like any other app or extension.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Model Context Protocol servers, VS Code, Midscene
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 39,516
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is UI-TARS-desktop free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use UI-TARS-desktop?
- No. Download and install it like any other app or extension.
- What does UI-TARS-desktop work with?
- According to its own documentation, it works with Model Context Protocol servers, VS Code, and Midscene.
- What is UI-TARS-desktop good for?
- Automating repetitive clicks and typing on your computer, changing settings in desktop apps without navigating menus, operating a browser to complete multi-step web tasks, and controlling a remote computer or browser from another device.
Similar agents to UI-TARS-desktop
- OpenHuman
OpenHuman is a desktop app and Rust library that runs many AI agents cheaply on a small server for developers and people who want a personal agent.
- Rakazo
Rakazo is a self-hosted AI assistant that runs persistent bots with memory and routines for people who want to pick their own model and computer.
- Andee
Andee is an agent app that lives on your Android phone or Mac and operates any app for you, without integrations.
- nanoMuse
nanoMuse is a personal agent app that runs tasks across your phone, computer, and browser, asking before anything irreversible.
- Xiryn
Xiryn is a self-hosted personal agent that runs tasks on its own Linux desktop in Docker, keeping your data on your own computer.
- cua
Cua is a set of tools that gives AI agents full desktops they can operate for people who need work done on their computer.