Browser Use + Scrapeless: An Undetected Cloud Browser for AI Agents

TL;DR:

• Browser Use drives a browser with an LLM; Scrapeless gives that browser a clean identity. Point the agent's cdp_url at the Scrapeless cloud browser and it runs on real Chromium, a consistent fingerprint, and residential egress — your agent code is unchanged.
• A local browser leaks automation on three axes: the navigator.webdriver tell, headless-default fingerprint, and your own exit IP. Anti-bot systems score all three at once.
• The integration is one line — the connection URL. Build wss://browser.scrapeless.com/api/v2/browser with your token and hand it to Browser(cdp_url=...).
• Watch the agent live from the session URL in the Scrapeless Dashboard while it reasons and clicks.
• Verified live: an agent connected over CDP, ran seven steps, and returned the target page's title through the Scrapeless cloud browser.
• Free to start. New Scrapeless accounts include free Scraping Browser runtime — sign up at app.scrapeless.com.

Introduction: give your agent a browser that reads clean

Browser Use lets a language model operate a real browser — it decides the steps, clicks the elements, and reads the page. Run it against a local Chrome and the agent inherits everything that makes automation obvious: it announces itself through the navigator.webdriver property, ships headless-default fonts and canvas behavior, and exits from an IP reputation services already know.

Fixing that locally means maintaining stealth patches as Chromium and the anti-bots change. Browser Use connects to any CDP-speaking browser through cdp_url, and the Scrapeless Scraping Browser is a CDP-speaking browser reached over one WebSocket endpoint. So the agent's runtime, fingerprint, and exit IP move server-side, and the only thing your code changes is where the browser comes from.

What you can do with it

• Run agent tasks on anti-bot-protected sites — the cloud browser clears challenges during render.
• Localize behavior — pin proxyCountry so the agent sees a page as a visitor in that market would.
• Scale past your machine — sessions run in the cloud, not on your laptop.
• Keep the agent code identical — swap only the browser source; the Agent, task, and LLM stay put.
• Watch and debug live — the Scrapeless Dashboard streams the running session.

Why Scrapeless Scraping Browser

The Scrapeless Scraping Browser is a customizable, anti-detection cloud browser designed for web crawlers and AI agents. For Browser Use specifically, it brings:

• Real self-developed Chromium that runs JavaScript exactly like Chrome, so SPAs and challenges resolve.
• A consistent per-session fingerprint — no navigator.webdriver tell, no headless defaults.
• Residential egress in 195+ countries, chosen per session with one proxyCountry value.
• A single CDP surface — every option is a query parameter on the same WebSocket endpoint.

Get your API key on the free plan at app.scrapeless.com.

Prerequisites

• Python 3.11 or newer (Browser Use requires 3.11+)
• An OpenAI API key for the agent's language model
• A Scrapeless account and API key — sign up at app.scrapeless.com

Full connection details live in the Scraping Browser documentation.

Install

pip install browser-use

For agent memory on longer tasks (Python < 3.13):

pip install "browser-use[memory]"

Connect your agent to the cloud browser

Build the Scrapeless WebSocket URL and pass it to Browser(cdp_url=...). navigator.webdriver is a signal that the W3C WebDriver specification requires conforming drivers to set — the cloud browser does not carry it.

import os
from urllib.parse import urlencode
from browser_use import Browser

def scrapeless_browser() -> Browser:
    params = {
        "token": os.environ["SCRAPELESS_API_KEY"],
        "sessionTTL": 900,
        "proxyCountry": "ANY",
    }
    ws = f"wss://browser.scrapeless.com/api/v2/browser?{urlencode(params)}"
    return Browser(cdp_url=ws)

Run the agent

Browser Use connects to the cloud browser over the Chrome DevTools Protocol, so the Agent runs exactly as it would locally.

Note: running this needs a live Scrapeless session and an OpenAI API key for agent.run(). Supply both to execute it.

import os
import asyncio
from urllib.parse import urlencode
from dotenv import load_dotenv
from browser_use import Agent, Browser, ChatOpenAI

def scrapeless_browser() -> Browser:
    params = {"token": os.environ["SCRAPELESS_API_KEY"], "sessionTTL": 900, "proxyCountry": "ANY"}
    ws = f"wss://browser.scrapeless.com/api/v2/browser?{urlencode(params)}"
    return Browser(cdp_url=ws)

async def main():
    load_dotenv()
    browser = scrapeless_browser()
    await browser.start()

    agent = Agent(
        task="Go to Google, search for 'Scrapeless', open the first result and return its title",
        llm=ChatOpenAI(model="gpt-4o"),
        browser=browser,
    )
    print(await agent.run())
    await browser.kill()

asyncio.run(main())

What you get back

In a live run the agent connected over cdp_url, ran seven steps, and returned the target page's title — Effortless Web Scraping Toolkit for Business and Developers — through the Scrapeless cloud browser. A few honest observations:

• The navigator.webdriver signal is absent, so the first check a site runs reads like a real Chrome.
• The exit IP matches proxyCountry — geo-gated pages resolve as a local visitor sees them.
• The agent adapts — when one search path shows a challenge, an LLM-driven agent can route around it and still reach the target, because it reasons about the page rather than following a fixed script.
• Memory is optional — enable it for long multi-step tasks with enable_memory=True on the Agent.

Conclusion: same agent, cleaner browser

Browser Use decides what to do; Scrapeless decides how the browser looks to the site. The integration is a single connection URL — build wss://browser.scrapeless.com/api/v2/browser with your token, hand it to Browser(cdp_url=...), and run your agent unchanged. For wiring more than one Python tool to the same cloud browser, see the undetected-fingerprint guide, and compare plans on the Scrapeless pricing page.

Ready to Build Your AI-Agent Scraping Pipeline?

Join our community to claim a free plan and connect with developers building agent pipelines: Discord · Telegram.

Sign up at app.scrapeless.com for free Scraping Browser runtime and point your Browser Use agent at the cloud browser your targets can't fingerprint.

FAQ

Q: Do I have to change my Browser Use agent code?
No. You change where the browser comes from — swap a local launch for Browser(cdp_url=<scrapeless url>). The Agent, task, and LLM are identical.

Q: Why not just run local Chrome?
Local Chrome runs on your IP, announces automation through navigator.webdriver, and needs you to maintain stealth patches. Scrapeless is a managed cloud browser with bundled residential egress and a consistent fingerprint — same API, none of the upkeep.

Q: Do I need a proxy?
No. Residential egress is built in — set proxyCountry to a region or ANY.

Q: Which Python version do I need?
Browser Use requires Python 3.11 or newer; agent memory additionally needs Python below 3.13.

Q: Can I watch the agent run?
Yes — the Scrapeless Dashboard streams the live session while the agent reasons and clicks.