Skip to main content
Browser Use turns a task into browser actions. This guide runs both the agent and Chromium inside one isolated microsandbox.
The browser image is large. Its first pull and Python package install can take a few minutes. Use a snapshot to avoid repeating that setup.

Run Browser Use

1

Create the agent

Save this as browser-use-task.py:
2

Start the sandbox

Save msb-trust.sh beside browser-use-task.py. Export a Browser Use API key, then run the task. The secret stays on the host and can only be substituted into requests to Browser Use’s model endpoint.
The agent prints its final result and exits. The Browser Use browser session uses the Chromium already included in the image, so it does not download a second browser.The script configures Chromium’s certificate trust for TLS interception used by --secret. See Trusting certificates in applications.
3

Clean up

Remove the stopped sandbox and unset the API key:

Reference