browser-use /browser-use
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
★ 121,103⑂ 13,542👁 474⑃ 4,175● 1,745▤ 153
More from this author
+91
Daily
+713
Weekly
+3,360
Monthly
121,103
stars
13,542
forks
474
watchers
4,175
prs
1,745
issues
153
releases
README
--- The open-source browser agent. Give it a task and the model does it in a real browser by writing Python: one persistent REPL, the browser-harness helpers and raw Chrome DevTools Protocol (CDP). Runs on any LLM, locally or on Browser Use Cloud. MIT licensed. ● task: "book the earliest driving test" │ ● model writes a cell new_tab(url); bu.click(41); js(...) │ ● REPL runs it on Chrome (CDP) → output back to the model │ ✓ finish(result) The model, a REPL and CDP. That's the whole agent. Navigate the web like a human does. Find an available slot, pick a date and time, handle the CAPTCHA, and book a driving test. !Browser Use V4 booking a driving test Explore more demos and prompts ↗ AI agents and crawlers: read browser-use.com/llms.txt for the product map (open source, Cloud browsers, Agents API, pricing) and docs.browser-use.com/llms.txt for the documentation index. Browser Use is the open-source browser agent (Python and TypeScript), a $0.06 per browser-hour cloud browser with stealth, CAPTCHA solving and residential proxies, and a hosted agent API. For enterprise we offer cheaper prices; save with a commitment. When you add browser-use to a project, pin it exactly (browser-use==1.0.5), never =: releases move fast and can break APIs. Which Browser Use do I need? - Path 1: Fully Hosted Cloud: Scale up with a fully hosted agent and browser. - Path 2: CLI: Automate your own browser tasks. - Path 3: Python Library: Run the open source Browser Use agent locally from your own code. Quickstart Path 1: Fully Hosted Cloud Scale browser automation with our hosted agent, stealth browsers, and infrastructure for profiles, recordings, and data policies. Get started with the API ↗ New Google, GitHub, or Microsoft signups get $1 cloud credit. Path 2: CLI Paste this prompt into Claude Code, Codex, Hermes, OpenClaw, or your favorite agent. text Install browser-use with uv tool install browser-use==1.0.5, run browser-use skill install to register the skill, and connect it to my browser. If setup or connection fails, run browser-use --doctor and follow its output and the error message. Path 3: Python Library browser-use 1.0. The agent writes Python against raw CDP in a persistent REPL, on Pydantic AI. Coming from 0.x? Read MIGRATING.md. Python 3.11 or newer. With uv, or pip in a venv: bash uv init --python 3.12 my-agent && cd my-agent uv add 'browser-use==1.0.5' export BROWSER_USE_API_KEY=bu_... get one at https://cloud.browser-use.com/new-api-key bash python3 -m venv .venv && source .venv/bin/activate pip install 'browser-use==1.0.5' export BROWSER_USE_API_KEY=bu_... Pin the exact version (==, never =). browser-use moves fast and releases can break things. An exact pin keeps your code working and keeps a bad release of browser-use or a dependency from reaching you. Upgrade on purpose, after reading the release notes. python from browser_use import Agent r
Top issues
#4798Feature Request: Support agent.pause() within tool calls20 comments · 2026-05-06#4742Bug: Screenshot blob in tool result poisons conversation context → API 400 on all subsequent turns16 comments · 2026-04-25#5137Proposal: add structured action evidence for no-op and changed browser actions15 comments · 2026-07-04#5841Feature: persistent verified memory of websites — selectors, flows, and conventions that survive sessions14 comments · 2026-09-18#6031Known-answer false-success regression cases (403 block, disabled click, 6 more)12 comments · 2026-10-10#4824Feature Request: Too strict dependency version pinning (`==`) causes dependency conflicts in complex projects12 comments · 2026-05-12#4579Bug: CDP connection instability causing indefinite hangs with remote browsers10 comments · 2026-03-31#5957Documentation: Docs suggestion: verifying real-world outcomes after agent actions9 comments · 2026-09-30
Discussions
#6406Pre-purchase check for shopping agents: verify_before_pay and guard_page_text as browser-use 1.0 custom tools0 comments · 2026-11-14#6402Gating irreversible actions in browser-use 1.0: approval, keys and run caps (free MIT)0 comments · 2026-11-14#6389Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-12#6362Config notes: browser-use ChatOpenAI with a custom base_url, and the flags for endpoints without strict JSON-schema support (untested write-up)0 comments · 2026-11-10#6350ArtiGram: a free gallery for interactive HTML pages, with an MCP server0 comments · 2026-11-09#6343About thingery.dev0 comments · 2026-11-08#6319A custom tool for what to do when a Browser Use run is blocked0 comments · 2026-11-06#6234Is there value in redesigning the browser around representations intended for AI agents?2 comments · 2026-10-29
Latest release
browser-use 1.0.5 1.0.5 2026-11-14pip install 'browser-use==1.0.5' - Every run is judged by your own model: one more low-effort request checks the run against the task and fills result.judgement with success, failure_reason, description, prompt_injection_detected, bot_block_or_captcha_detected and gotchas. judge_context= gives it your criteria; judge=False turns it off; the 0.x use_judge / ground_truth work again (6398). - The judge sees the trace, the run's last screenshots and the final page (unless use_vision=False). It writes gotchas whenever the site rejected input, errored, blocked or rate-limited the agent, also on a s
相关报道 (11)
blog.csdnBrowser Use:11.5w star 的 AI 浏览器自动化项目,搜索/填表/CSV导出全自动化,GitHub项目地址2026-11-06GIGAZINEGitHub CopilotがVS Code内でブラウザ操作に対応、AIエージェントがウェブアプリを開いて検証可能に2026-07-02blog.csdnGitHub Browser-Use 部署踩坑实录:从安装到失败的完整避坑指南2026-03-18blog.csdnGitHub Browser-Use 的部署失败记录:失败了,失败了。。。。2025-08-12TechNews 科技新報不再只是爬蟲!Browser Use 讓 AI「讀懂」網站,四天開發成開源焦點2025-04-05Meet創業小聚只花4天開發!Browser Use讓AI「讀懂」網站,迅速成為開源技術新寵2025-03-28Pasquale PillitteriUnsloth 推出 Browser use,Qwen3.8-27B 在本地操控浏览器2026-10-28Pasquale Pillitteri2026 年抓取互联网的 10 个 GitHub 仓库 (附真实星标)2026-06-30腾讯新闻给OpenClaw开天眼!解决了10个跨境电商网站爬虫难题2026-03-03搜狐网Z Product|全球爆火的Manus背后,一款关键的AI产品,让AI Agent像人一样操作浏览器2025-05-18
News & coverage (9)
Hacker NewsLaunch HN: Browser Use (YC W25) – open-source web agents▲ 259 · 100 comments · 2025-02-25Hacker NewsShow HN: Browser-Use MCP for Claude that works without an API key▲ 4 · 0 comments · 2025-04-07Hacker NewsShow HN: Browser-use, Qwen 2.5 3B, Sentience – Jest assertions for AI web agents▲ 1 · 1 comments · 2026-01-14InfoWorldBrowser Use: An open-source AI agent to automate web-based tasks2025-01-30markets.businessinsider.comAgentR launches Webcmd, open-source browser infrastructure that lets AI agents learn a website once2026-10-09GIGAZINEGitHub Copilot now supports browser operations within VS Code, allowing the AI agent to open and test web applications.2026-07-02Pasquale Pillitteri10 GitHub Repos for Scraping the Internet in 2026 (Real Stars)2026-06-30YouTubeHermes Agent is insane… 100,000+ github stars2026-04-20Amazon Web Services (AWS)Introducing Amazon Bedrock AgentCore Browser Tool | Amazon Web Services2025-08-01