browser-use

Make websites accessible for AI agents

browser-use Permissive license Active ★ 109,110 v0.13.7 released 2026-07-27

Install

browser-use on PyPI

pip

pip install browser-use

uv

uv add browser-use

poetry

poetry add browser-use

Package facts

License	not declared (permissive)
Python support	supports the current Python release (<4.0,>=3.11)
Install friction	low — pure-Python wheel
Runtime dependencies	36 — aiohttp, anthropic, anyio, browser-harness, browser-use-sdk, bubus, cdp-use, click, cloudpickle, google-api-core, google-api-python-client, google-auth-oauthlib, google-auth, google-genai, groq, httpx, inquirerpy, markdownify, mcp, ollama, openai, pillow, posthog, psutil, pydantic, pyobjc, pyotp, pypdf, python-docx, python-dotenv
Maintenance	actively maintained — 17 days since the last release
Last repo commit	2026-08-13
First released	2024-11-06
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: browser_use-0.13.7-py3-none-any.whl

License :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3

About browser-use

from the package's own PyPI description — quoted content, verbatim

<picture> <source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/2ccdb752-22fb-41c7-8948-857fc1ad7e24"> <source media="(prefers-color-scheme: dark)" srcset="https://github.com/user-attachments/assets/774a46d5-27a0-490c-b7d0-e65fcbbfa358"> <img alt="Shows a black Browser Use Logo in light color mode and a white one in dark color mode." src="https://github.com/user-attachments/assets/2ccdb752-22fb-41c7-8948-857fc1ad7e24" width="full"> </picture>

<div align="center"> <a href="https://cloud.browser-use.com?utm_source=github&utm_medium=readme-badge-downloads"><img src="https://media.browser-use.tools/badges/package"...

Read as markdown · JSON record · Source repository · Homepage · Docs

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Browser Use is a Python library that lets AI agents control web browsers programmatically—opening pages, clicking buttons, typing text, and filling forms—to automate web tasks like form completion, data extraction, and QA testing.

Low friction: pure Python wheel with no compiled dependencies. Active maintenance (latest release 2026-07-27, 17 days old) and strong community signal (109110 GitHub stars). Requires Python 3.11+ and 36 runtime dependencies including LLM client libraries (anthropic, openai, google-genai, groq) and browser tooling (browser-harness, browser-use-sdk).

MIT license (permissive) allows free commercial and private use with minimal restrictions—you may use, modify, and distribute browser-use in proprietary projects provided you retain the license notice.

Usage

pip install browser-use

import asyncio
from browser_use import Agent, ChatBrowserUse

async def main():
    agent = Agent(
        task="Find the number of stars of the browser-use repo",
        llm=ChatBrowserUse(model='openai/gpt-5.5'),
    )
    history = await agent.run()

asyncio.run(main())

Requires Python 3.11 or later; an LLM API key (Browser Use Cloud, OpenAI, Anthropic, Google, or Groq) set in .env as BROWSER_USE_API_KEY or provider-specific key; browser-harness installation may require system dependencies—see https://github.com/browser-use/browser-harness/blob/main/install.md if setup fails.

Verdict: Browser Use is a well-maintained, actively developed library (top 1000 PyPI tier, zero known vulnerabilities) for building AI-driven web automation. Its permissive MIT license and low install friction make it accessible; the large dependency tree (36 runtime packages) reflects its role as a full-stack agent framework rather than a lightweight utility. Suitable for production web automation, QA, and data extraction workflows paired with any major LLM provider.

Needs verification

Whether browser-harness system dependencies (Chromium, display server) are documented or auto-installed on all major OS platforms
Performance characteristics and rate limits when running many parallel tasks or against rate-limited sites
Data retention and privacy implications of using Browser Use Cloud service vs. self-hosted browser-harness

ai web automationbrowser agent pythonweb scraping with llmautomated form fillingweb task automationbrowser control apiai web testing