AgentToolDrop

51 of 71

UI-TARS Desktop

Controls your computer and browser from screenshots, with mouse and keyboard actions chosen by a vision model

Download from GitHub releases or install with Homebrew

brew install --cask ui-tars

Copied from the project's docs at github.com/bytedance/UI-TARS-desktop/blob/main/docs/quick-start.md

Why you'd want it

The repo ships two ByteDance projects. UI-TARS Desktop is a desktop app with a native GUI agent driven by the UI-TARS and Seed-1.5-VL/1.6 vision-language models: it takes screenshots, recognizes what is on screen and controls the mouse and keyboard to follow natural-language instructions, with local computer and browser operators. Agent TARS is a separate CLI and Web UI agent that controls browsers through visual grounding, the DOM or a hybrid of both, and can mount MCP servers to reach other tools.

Best for

  • Experimenting with vision-based computer use
  • Automating desktop apps that have no API
  • Running an open GUI agent model you deploy yourself

Use it when

You want an agent that operates desktop apps or a browser by looking at the screen, and you can point it at a UI-TARS model endpoint, for example one deployed on Hugging Face.

Skip it if

You use more than one monitor (the quick start says only single-monitor setups are supported) or want a library to embed in your own code. The free remote operator service was discontinued on August 20, 2025.

Editor's note

The same repo also hosts Agent TARS, a separate CLI and Web UI agent started with npx @agent-tars/cli@latest.

Related tools

Same category or shared tags, by drop score.

  1. Rank 14

    Browser Use

    Browser agent

    Lets an LLM drive a real browser to complete multi-step web tasks from Python code or a CLI

    • score 69
    • 118k stars
    • pushed
    • 0.13.11 on
    • MIT

    Install with uv

    uv add browser-use
    Use it when, skip it if, stats for Browser Use

    Why you'd want it

    Browser Use is an open-source browser agent: you give it a task in plain language and a model, and it opens a browser, works through the site and returns a result. It works with OpenAI, Anthropic and Google models or local models through Ollama, accepts custom tools registered as Python functions, and can drive a local Chrome profile, a remote browser over CDP or a Browser Use Cloud browser. A CLI gives existing agents such as Claude Code, Codex and Cursor browser access, and an integration implements Claude's browser toolset with Browser Use as the driver.

    Best for

    • Python apps that automate tasks on real websites
    • Giving a coding agent browser access
    • Projects that may move to hosted browsers later

    Use it when

    You want an agent that completes tasks on live websites, such as forms, bookings and lookups, from your own Python code with your choice of model.

    Skip it if

    You only need fixed, scripted browser steps with no model in the loop. The library needs Python 3.11 or later, and stealth browsers, proxies and the BU2 model are paid Browser Use Cloud services.

    Stats

    Stars
    118,001
    Last push
    Release
    0.13.11,
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor
    Drop score
    69 of 100

    Full stat block for Browser Use

  2. Rank 58

    Stagehand

    Browser agent

    Adds natural-language act, observe and extract calls to Playwright-style browser code in TS, Python and Go

    Install with pnpm

    pnpm add @browserbasehq/stagehand 'zod@~4.4.3'
    Use it when, skip it if, stats for Stagehand

    Why you'd want it

    Stagehand mixes ordinary browser code (goto, click, locator) with three AI calls: act performs an action described in plain language, observe returns real selectors, and extract returns data validated against a Zod or Pydantic schema. Because observe hands back selectors, you can fill credentials yourself without sending them to the model, and the README says act, observe and extract refresh how an action happens when a site changes. It runs against a local Chrome or a Browserbase cloud browser, which adds a model gateway, server-side caching, proxies and session recordings.

    Best for

    • Developers who already write Playwright-style scripts
    • Structured data extraction from logged-in sites
    • TypeScript, Python or Go codebases

    Use it when

    You want to keep control of each browser step in code but let a model handle brittle selectors and data extraction.

    Skip it if

    You do not want to write browser code yourself. Caching, the model gateway and cloud browsers require a Browserbase API key, and local runs need Chrome installed.

    Stats

    Stars
    25,671
    Last push
    Release
    @browserbasehq/[email protected],
    License
    MIT
    Pricing
    Open source
    Drop score
    40 of 100

    Full stat block for Stagehand

  3. Rank 69

    Steel Browser

    Browser agent

    Runs a self-hostable browser API that manages Chrome sessions agents connect to with Puppeteer or Playwright

    • score 31
    • 7.8k stars
    • pushed
    • v0.5.4-beta on
    • Apache-2.0

    Run with Docker

    docker run -p 3000:3000 -p 9223:9223 ghcr.io/steel-dev/steel-browser
    Use it when, skip it if, stats for Steel Browser

    Why you'd want it

    Steel is an open-source browser API server: it manages sessions, pages and Chrome processes so your agent code connects to a ready browser with Puppeteer, Playwright or Selenium. Sessions keep cookies and local storage across requests, and the server includes proxy chain management, custom Chrome extensions, stealth plugins and fingerprint management, and a UI for viewing and debugging sessions. Quick action endpoints return a page's HTML, a screenshot or a PDF in one REST call, and the Node and Python SDKs work against both self-hosted Steel and Steel Cloud.

    Best for

    • Hosting your own browser infrastructure for agents
    • Stateful sessions with proxies and extensions
    • Teams already using Puppeteer, Playwright or Selenium

    Use it when

    Your agent needs remote, stateful browser sessions and you want to run them yourself in Docker or use the managed Steel Cloud.

    Skip it if

    You want something that decides what to do on a page: Steel provides the browser infrastructure, not the agent. The README describes the project as in public beta.

    Stats

    Stars
    7,805
    Last push
    Release
    v0.5.4-beta,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Docker
    Drop score
    31 of 100

    Full stat block for Steel Browser

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/ui-tars-desktop.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'