4 browser and computer use
Agents and infrastructure that drive a real browser or desktop on your behalf.
- Rank 14
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-useUse 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
- Rank 51
Controls your computer and browser from screenshots, with mouse and keyboard actions chosen by a vision model
- score 48
- 39.3k stars
- pushed
- v0.3.1 on
- Apache-2.0
Download from GitHub releases or install with Homebrew
brew install --cask ui-tarsUse it when, skip it if, stats for UI-TARS Desktop
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.
Stats
- Stars
- 39,279
- Last push
- Release
- v0.3.1,
- License
- Apache-2.0
- Pricing
- Open source
- Works with
- macOS, Windows
- Drop score
- 48 of 100
- Rank 58
Adds natural-language act, observe and extract calls to Playwright-style browser code in TS, Python and Go
- score 40
- 25.7k stars
- pushed
- @browserbasehq/stagehand@3.7.3 on
- MIT
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/stagehand@3.7.3,
- License
- MIT
- Pricing
- Open source
- Drop score
- 40 of 100
- Rank 69
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-browserUse 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