# UI-TARS-desktop

> UI-TARS-desktop — bytedance-ui-tars-desktop. Use this tool when you need to integrate cutting-edge AI models with agent infrastructure for multimodal interactions. It solves problems of disconnected AI systems and limited agent capabilities, enabling seamless communication between models and agents. The UI-TARS-desktop tool accepts AI model inputs and outputs agent infrastructures, ideal for use cases requiring coordinated AI agent interactions.

Canonical page: https://skillsregistry.net/skills/bytedance-ui-tars-desktop  
JSON: https://api.skillsregistry.net/v1/skills/bytedance-ui-tars-desktop

## Description

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/bytedance/UI-TARS-desktop)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "bytedance-ui-tars-desktop"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bytedance-ui-tars-desktop` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bytedance-ui-tars-desktop/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt