Browser Use

Point a Browser Use agent at Kernel browsers

Browser Use is an agent framework, not a browser host — so there’s nothing to port. You keep your agent code and change where its browser comes from.

If you’re running Browser Use against its own cloud, or against a local Chromium, this is the change.

Point the agent at a Kernel browser

Python

from browser_use import Agent, BrowserSession
from kernel import Kernel

kernel = Kernel()
kernel_browser = kernel.browsers.create(stealth=True, timeout_seconds=600)

session = BrowserSession(cdp_url=kernel_browser.cdp_ws_url)

agent = Agent(
    task="Find the top story on Hacker News and summarize it",
    browser_session=session,
)

try:
    await agent.run()
finally:
    kernel.browsers.delete_by_id(kernel_browser.session_id)

The full setup, including the model configuration and running it on the App Platform, is on the Browser Use integration page.

What you gain

	Local Chromium	Browser Use Cloud	Kernel
Where it runs	Your machine	Managed	Managed, microVM per browser
Watch a run	Your screen	Session viewer	Live view and replays
Logins	Your own cookie handling	Saved sessions	Managed auth and profiles
Bot detection	Whatever you patch in	Managed	Anti-detection by default, stealth, proxies
Co-locating the agent	—	—	App Platform
Per-step telemetry	—	—	Telemetry

Things to check

• Keep the default context and page. Kernel browsers launch with one already open. Browser Use handles this, but custom harness code should use contexts()[0] / pages()[0] rather than creating new ones.
• Set timeout_seconds. An agent that stalls shouldn’t leave a browser running — see termination.
• Concurrency is per plan. Running many agents at once is bounded by concurrency and limits.