pyagentbrowser 0.38.0

Native browser automation with typed Python APIs and before-and-after evidence.

Documentation · Get started · Examples · PyPI · Issues

Control browsers and iframe applications from Python with the native agent-browser engine. Bind page and frame handles, act on inspected elements, capture model-ready images, and retain before-and-after evidence.

Alpha: The public API and native integration can change between minor releases. Pin a version for production automation.

Get started

python -m pip install pyagentbrowser

Requires Python 3.11 through 3.14. Local browsers run headlessly by default. The first launch finds Chrome or Chromium, or downloads Chrome for Testing when needed.

from agentbrowser import Browser

with Browser.launch() as browser:
    browser.page.set_content(
        "<button onclick=\"this.textContent='Done'\">Run</button>"
    )
    snapshot = browser.page.observe()
    result = snapshot.one(role="button", name="Run").click()

    print(result.after.one(role="button").name)
    print(result.diff.changed)

Done
True

page.observe() captures a Snapshot of the page's accessible elements. Selecting a button returns a Ref. Clicking it returns an ActionResult with before, after, and diff. Use page.find for live element queries and page.frames for embedded applications.

Browser workflows

• Inspect and act. Navigate pages, fill forms, read documents, and capture screenshots and PDFs through typed namespaces.
• Keep document scope. Bind an exact page or frame so observation, evaluation, waits, scrolling, capture, and ref actions share one target.
• Deliver evidence. Read screenshot bytes and MIME metadata, and inspect structured snapshots and action results.
• Manage sessions. Launch a browser or attach to an existing one. Work with tabs, cookies, saved state, and explicit cleanup.
• Control actions. Configure domain restrictions and confirmation policy for operations through the native engine.
• Compose in Python. Use synchronous or asynchronous controllers, agent skills, and the complete engine protocol through browser.native.

Documentation

Get started · Concepts · Action evidence · Code-mode integration · Safety · API reference · Troubleshooting

The documentation site covers browser workflows, optional packages, supported platforms, and integrations. See examples for Python scripts and Contributing for development setup and checks.

License

pyagentbrowser is licensed under the Apache License 2.0. See NOTICE for bundled software attribution.