UI-TARS-desktop
This ByteDance repository hosts TARS, an open-source multimodal AI agent stack with two projects. Agent TARS is a general multimodal agent with a CLI and web UI that combines GUI-agent vision with DOM-based browser control and MCP tools, aiming to complete tasks the way a person would. UI-TARS Desktop is a native desktop application that lets a vision-language model, driven by the UI-TARS and Seed-VL series models, operate your local computer, a remote computer or a browser with mouse and keyboard.
It suits developers and researchers exploring computer-use agents: automating GUI tasks in desktop apps that have no API, multi-step browser tasks such as comparing and booking travel, or prototyping agents that see the screen. UI-TARS Desktop works on Windows and macOS and in the browser, with screenshot-based recognition and real-time status feedback; Agent TARS runs headful in a web UI or headless as a server and can mount additional MCP servers.
Getting started: run Agent TARS with `npx @agent-tars/cli@latest` (Node.js 22+ for a global install) and pass your model provider and API key, for example Volcengine or Anthropic. UI-TARS Desktop is a separate desktop app; follow its quick start to download it and configure a vision-language model endpoint.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-09
- Commits, last 90 days
- 8
- Releases, last 90 days
- 1
- Latest release
- v0.3.1 (2026-10-08)
- Open issues
- 511
- Recent issues with at least one comment
- 13/16
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #268 [Feature] Windows platform support for Agent TARS 23 comments · 2025-03-22
- #591 [Bug]: Missing clicks20 comments · 2025-05-13
- #587 [Bug]: UI-TARS-2B-SFT model maximum context length Error16 comments · 2025-05-13
- #11 no action after thinking12 comments · 2025-01-22
- #311 Mac已经按要求授权应用访问设备的权限,依然无法执行浏览器访问11 comments · 2025-03-24
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You want a visual GUI agent that understands native desktop screens and operates mouse/keyboard actions end-to-end via vision models.
- You want an open-source multimodal desktop application for cross-application task automation on macOS, Windows, and Linux.
- You only need web-browser-based automation; Playwright or Scrapling are much faster and more reliable via direct DOM.
- Your environment lacks a capable GPU or reliable multimodal LLM API with high vision resolution support.
How it differs
UI-TARS Desktop operates through visual GUI perception, mouse movements, and screen recognition. Open Interpreter operates primarily through the host CLI and executing generated Python, Bash, or AppleScript commands.
Compatibility
Quick start
Use cases
Alternatives
Comments
No comments yet. Be the first!