---
slug: "ui-tars-desktop"
name: "UI-TARS Desktop"
effect: "Controls your computer and browser from screenshots, with mouse and keyboard actions chosen by a vision model"
category: "browser-agent"
url: "https://github.com/bytedance/UI-TARS-desktop"
github: "bytedance/UI-TARS-desktop"
pricing: "open-source"
license: "Apache-2.0"
tags: ["computer-use", "gui-agent", "desktop-app", "vision-language-model", "multimodal"]
platforms: ["macos", "windows"]
install_kind: "download"
date_added: "2026-10-14"
drop_score: 48
stars: 39279
pushed_at: "2026-10-09T01:29:53Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T01:19:06.000Z"
page: "https://agenttooldrop.com/tools/ui-tars-desktop"
---

# UI-TARS Desktop

Controls your computer and browser from screenshots, with mouse and keyboard actions chosen by a vision model

Category: Browser and computer use. Pricing: Open source. License: Apache-2.0.

Platforms: macos, windows.

## Why you would want it

The repo ships two ByteDance projects. UI-TARS Desktop is a desktop app with a native GUI agent driven by the UI-TARS and Seed-1.5-VL/1.6 vision-language models: it takes screenshots, recognizes what is on screen and controls the mouse and keyboard to follow natural-language instructions, with local computer and browser operators. Agent TARS is a separate CLI and Web UI agent that controls browsers through visual grounding, the DOM or a hybrid of both, and can mount MCP servers to reach other tools.

## Best for

- Experimenting with vision-based computer use
- Automating desktop apps that have no API
- Running an open GUI agent model you deploy yourself

## Use it when

You want an agent that operates desktop apps or a browser by looking at the screen, and you can point it at a UI-TARS model endpoint, for example one deployed on Hugging Face.

## Skip it if

You use more than one monitor (the quick start says only single-monitor setups are supported) or want a library to embed in your own code. The free remote operator service was discontinued on August 20, 2025.

## Editor note

The same repo also hosts Agent TARS, a separate CLI and Web UI agent started with npx @agent-tars/cli@latest.

## Install

Download from GitHub releases or install with Homebrew:

```sh
brew install --cask ui-tars
```

Source: https://github.com/bytedance/UI-TARS-desktop/blob/main/docs/quick-start.md

## Live signals

Fetched 2026-10-15T01:19:06.000Z (status: ok).

- Repository: bytedance/UI-TARS-desktop
- Stars: 39,279
- Forks: 3,985
- Open issues and PRs: 500
- License (GitHub): Apache-2.0
- Last push: 2026-10-09
- Latest release: v0.3.1 (2026-10-08)

## Links

- Website: https://github.com/bytedance/UI-TARS-desktop
- GitHub: https://github.com/bytedance/UI-TARS-desktop
- Install instructions verified at: https://github.com/bytedance/UI-TARS-desktop/blob/main/docs/quick-start.md
- Source for this entry: https://github.com/bytedance/UI-TARS-desktop#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/ui-tars-desktop
- Full catalog (JSON): https://agenttooldrop.com/tools.json