UI-TARS Desktop

Not yet reviewedagentsPrompt / Rule# agents # multimodal # computer-use # browser # mcp

Open-source multimodal AI agent stack connecting models and agent infrastructure.

Not yet reviewed (manual audit pending)

This skill is cataloged from open community sources and has not yet completed full manual verification. Inspect repository code prior to local execution.

What is UI-TARS Desktop?

UI-TARS Desktop is a multimodal agent stack for GUI, browser, and computer-use workflows built around modern agent infrastructure.

How to use UI-TARS Desktop?

Use it when you need desktop or browser-operating agents that combine multimodal models with agent orchestration patterns.

Key features of UI-TARS Desktop

✓Multimodal agent stack
✓GUI and browser-use workflows
✓Computer-use positioning
✓MCP-compatible ecosystem relevance

When to use UI-TARS Desktop

1Desktop agent automation
2Computer-use experimentation
3Multimodal agent prototyping

Installation & Setup Guide

Agent Rules / Prompt Setup

git clone --depth 1 https://github.com/sickn33/antigravity-awesome-skills.git /tmp/ag-skills && mkdir -p ~/.gemini/config/skills && cp -r /tmp/ag-skills/skills/ui-tars-desktop ~/.gemini/config/skills/

Security Review Status

Not yet reviewed (manual audit pending)

This skill is cataloged from open community sources and has not yet undergone full manual line-by-line security verification by our team.

Recommended Verification Steps Prior to Execution:

Inspect the source repository files before adding to your local AI tool config.
Avoid passing production API credentials or sensitive filesystem permissions unless explicitly required.
Run initial commands inside a sandboxed terminal or container environment.

Source repository link for manual inspection: https://github.com/bytedance/UI-TARS-desktop