bytedance / UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Why this job: topics: computer-use, gui-agent, browser-use
What it does
- One-Click Out-of-the-box CLI. Supports both headful Web UI and headless server execution.
- Hybrid Browser Agent. Control browsers using GUI Agent, DOM, or a hybrid strategy.
- Event Stream. Protocol-driven Event Stream drives Context Engineering and Agent UI.
- MCP Integration. The kernel is built on MCP and also supports mounting MCP Servers to connect to real-world tools.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 31 days ago
- Stars
- 39,583
- +71 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.3.1
- Released 32 days ago
- Built with
- TypeScript
- 89% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 38% closed
- 359 still open
- Pull requests
- 1,082 merged
- 153 waiting
- Releases
- 39
- 1 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| TurixAI / TuriX-CUA | 3,176 | 56 days ago | MIT | No downloads |
| OmniJev / OneJev | 251 | yesterday | Apache-2.0 | No downloads |
| steel-dev / steel-browser | 7,939 | yesterday | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- TypeScript 89%
- MDX 8%
- CSS 1%
- JavaScript 1%
Topics
- agent
- agent-tars
- browser-use
- computer-use
- cowork
- gui-agent
- gui-operator
- mcp
- mcp-server
- multimodal
- tars
- ui-tars
Project record
- JobAutomation and scraping
- StatusListed
- Commits1,118
- Forks4,028
- Watching277
- Stars in 28 days+417
- CreatedJan 19, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026