Browser Use: 94K+ Stars — 2026年 AI 浏览器自动化基准测试与实战

from browser_use import Agent, Browser
from langchain_openai import ChatOpenAI
import asyncio

async def main():
    browser = Browser()
    agent = Agent(
        task="Find the number of stars of the browser-use repo",
        llm=ChatOpenAI(model="gpt-4.1"),
        browser=browser,
    )
    result = await agent.run()
    print(result)

if __name__ == "__main__":
    asyncio.run(main())

# 使用 uv（推荐）
uv init
uv add browser-use
uv sync

# 使用 pip
pip install browser-use

# 安装 Chromium（如果尚未安装）
playwright install chromium

# .env 文件
OPENAI_API_KEY=sk-your-openai-key
ANTHROPIC_API_KEY=sk-ant-your-anthropic-key
GOOGLE_API_KEY=your-google-api-key

# 可选：Browser Use Cloud 隐身浏览器
BROWSER_USE_API_KEY=your-cloud-key

import asyncio
from browser_use import Agent, Browser, ChatBrowserUse

async def main():
    browser = Browser()
    agent = Agent(
        task="List the top 20 posts on Hacker News today with their points",
        llm=ChatBrowserUse(),
        browser=browser,
    )
    result = await agent.run()
    print(result.output)

if __name__ == "__main__":
    asyncio.run(main())

# Dockerfile
FROM python:3.11-slim

WORKDIR /app
RUN pip install browser-use playwright
RUN playwright install chromium
RUN playwright install-deps

COPY . .
CMD ["python", "agent.py"]

# docker-compose.yml
version: '3.8'
services:
  browser-use:
    build: .
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
    volumes:
      - ./scripts:/app
    command: python agent.py

from browser_use import Agent, Browser
from langchain_openai import ChatOpenAI
import asyncio

async def search_flights():
    agent = Agent(
        task="Find the cheapest flight from NYC to London next week",
        llm=ChatOpenAI(model="gpt-4o", temperature=0),
        browser=Browser(),
    )
    return await agent.run()

asyncio.run(search_flights())

from browser_use import Agent, Browser
from langchain_anthropic import ChatAnthropic
import asyncio

async def extract_data():
    agent = Agent(
        task="Extract all pricing plans from example.com/pricing",
        llm=ChatAnthropic(model="claude-sonnet-4-6"),
        browser=Browser(),
    )
    result = await agent.run()
    print(result.output)

asyncio.run(extract_data())

from browser_use import Agent, Browser
from langchain_google_genai import ChatGoogleGenerativeAI
import asyncio

async def research_topic():
    agent = Agent(
        task="Research the latest AI news and summarize top 5 stories",
        llm=ChatGoogleGenerativeAI(model="gemini-3-flash-preview"),
        browser=Browser(),
    )
    return await agent.run()

asyncio.run(research_topic())

from browser_use import Agent, Browser
from langchain_ollama import ChatOllama
import asyncio

async def local_automation():
    agent = Agent(
        task="Fill out the contact form on example.com/contact",
        llm=ChatOllama(model="qwen2.5:72b"),
        browser=Browser(),
    )
    return await agent.run()

asyncio.run(local_automation())

from playwright.async_api import async_playwright
from browser_use import Agent
from langchain_openai import ChatOpenAI

async def hybrid_automation():
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        
        # 确定性 Playwright 步骤
        await page.goto("https://example.com")
        
        # 将复杂任务移交给 Browser Use 智能体
        agent = Agent(
            task="Navigate to pricing and extract all plan details",
            llm=ChatOpenAI(model="gpt-4o"),
            browser=browser,
        )
        result = await agent.run()
        await browser.close()
        return result

import asyncio
from browser_use import Agent, Browser
from langchain_openai import ChatOpenAI

async def monitor_prices():
    urls = [
        "https://amazon.com/dp/B0DHTYW7P5",
        "https://bestbuy.com/site/xyz",
        "https://newegg.com/product/abc",
    ]
    
    results = []
    for url in urls:
        agent = Agent(
            task=f"Go to {url} and extract the current price, availability, and seller name",
            llm=ChatOpenAI(model="gpt-4o-mini"),
            browser=Browser(),
        )
        result = await agent.run()
        results.append({"url": url, "data": result.output})
    
    return results

# 通过 cron 或定时任务每日运行
prices = asyncio.run(monitor_prices())

import asyncio
from browser_use import Agent, Browser
from langchain_openai import ChatOpenAI

async def run_parallel_agents(tasks):
    browser = Browser()
    agents = [
        Agent(task=task, llm=ChatOpenAI(model="gpt-4o-mini"), browser=browser)
        for task in tasks
    ]
    results = await asyncio.gather(*[agent.run() for agent in agents])
    return results

tasks = [
    "Find iPhone 16 price on Amazon",
    "Find iPhone 16 price on Best Buy",
    "Find iPhone 16 price on Apple Store",
]

results = asyncio.run(run_parallel_agents(tasks))

from browser_use import Browser, BrowserConfig
from browser_use import Agent
from langchain_openai import ChatOpenAI

config = BrowserConfig(
    proxy={
        "server": "http://proxy.example.com:8080",
        "username": "user",
        "password": "pass",
    },
    headless=True,
)

browser = Browser(config=config)
agent = Agent(
    task="Extract data from a geo-restricted site",
    llm=ChatOpenAI(model="gpt-4o"),
    browser=browser,
)

from browser_use import Browser, BrowserConfig, Agent
from langchain_openai import ChatOpenAI

# 使用持久化浏览器配置文件来保持 Cookie 和登录状态
config = BrowserConfig(
    user_data_dir="./browser_profile",
    headless=False,  # 初始登录使用有头模式
)

async def authenticated_task():
    browser = Browser(config=config)
    agent = Agent(
        task="Download my monthly invoice from the billing page",
        llm=ChatOpenAI(model="gpt-4o"),
        browser=browser,
    )
    return await agent.run()

import asyncio
from browser_use import Agent, Browser
from langchain_openai import ChatOpenAI

async def robust_agent(task, max_retries=3):
    for attempt in range(max_retries):
        try:
            agent = Agent(
                task=task,
                llm=ChatOpenAI(model="gpt-4o"),
                browser=Browser(),
                max_steps=25,  # 限制步数防止无限循环
            )
            result = await agent.run()
            if result.success:
                return result
        except Exception as e:
            print(f"Attempt {attempt + 1} failed: {e}")
            await asyncio.sleep(2 ** attempt)  # 指数退避
    raise Exception(f"Task failed after {max_retries} attempts")

from prometheus_client import Counter, Histogram, start_http_server
from browser_use import Agent, Browser

agent_runs = Counter("browseruse_agent_runs_total", "Total agent runs")
agent_failures = Counter("browseruse_agent_failures_total", "Total agent failures")
agent_duration = Histogram("browseruse_agent_duration_seconds", "Agent run duration")

start_http_server(8000)

async def monitored_agent(task):
    agent_runs.inc()
    with agent_duration.time():
        try:
            agent = Agent(task=task, llm=llm, browser=Browser())
            result = await agent.run()
            return result
        except Exception:
            agent_failures.inc()
            raise