#1616th of 17 in Agent platforms

ui-tars-desktop

Multimodal agent stack: terminal/Web UI agent and a desktop GUI agent

Documentation ↗ Website ↗ Repository on GitHub ↗

Stars: 39.3k
License: Apache-2.0
Last commit: Oct 2026
Last release: Oct 2026
Language: TypeScript

Stars, last 29 weeks+10,732

28,547 on 25 Mar 202639,279 on 14 Oct 2026

From GitHub's daily star counts.

Checked 15 Oct 2026 on GitHub.

Overview

Monorepo with two projects. Agent TARS is a CLI and Web UI agent that controls a browser via GUI vision, DOM, or a hybrid, and mounts MCP servers as tools. UI-TARS Desktop is an app that operates the local or a remote computer and browser through the UI-TARS and Seed-1.5-VL/1.6 vision-language models.

Who it is for: Developers wanting GUI and browser-operating agents driven by vision models

Strengths

Browser control by GUI vision, DOM, or hybrid strategy
MCP kernel; external MCP servers can be mounted as tools
Agent TARS runs headful (Web UI) or headless as a server
Works with providers such as Volcengine and Anthropic via CLI flags

Weaknesses

Two products in one repo; README splits setup across external docs
Desktop app targets Windows and macOS; Linux support not stated
RAM and GPU needs for local UI-TARS models are not stated
Agent TARS CLI requires Node.js 22 or newer

What it needs

Needs Node.js >= 22, model provider API key
Models: UI-TARS-1.5, Seed-1.5-VL, Volcengine Doubao, Anthropic Claude

Also in Agent platforms

See all 17

Also in Agent platforms
Rank	Project	Score
1	LangflowVisual builder for AI agents and workflows, exposed as API or MCP server155.7k starsMIT	80 out of 100
2	daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps66.4k starsMIT	77 out of 100
3	deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks83.9k starsMIT	75 out of 100
#4	DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)158.5k starscustom license	74 out of 100
#5	MulticaIssue board where AI coding agents take assignments like teammates52.8k starscustom license	72 out of 100

How to choose

Decide between a visual builder (faster to start) and code-first (easier to test and version).
Check how workflows are exported; vendor-specific JSON makes migration costly.
Look at the license for the server part; several are AGPL or source-available.

Health

Releases: 2 in the last 12 monthsLast one 7 days ago
Top contributor: 31% of commits14 of 45 in the last 12 months
Security advisories: NoneOn GitHub, in the last 12 months
OpenSSF Scorecard: 5.9 out of 10 ↗ (opens in a new tab)Run by OpenSSF on 24 Feb 2026

Read from GitHub, deps.dev and OpenSSF on 15 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

Apache-2.0 Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#16 of 17 in Agent platforms on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/bytedance/ui-tars-desktop.svg)](https://archestack.com/best-of-ai/projects/ui-tars-desktop/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-ai/ui-tars-desktop/" title="ui-tars-desktop on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Open-Source AI on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with ui-tars-desktop filled in.