Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

1.8 KB
Raw Blame

README artwork, diagram, and demo sources

Header artwork

The orange key-shaped bridge is an existing painting from the Browser Use website. The README displays the original image at a maximum width of 720 pixels and links it to the website. It is hosted on the website, so cloning the repository does not download the artwork.

Product diagram

which-product-{light,dark}{,-mobile}.svg are copied from the SDK docs, where scripts/diagrams/ generates them (task docs:diagrams). Regenerate there and copy the four files here; phones under 600 px get the mobile variants.

The figure shows the README's three paths: the hosted V4 agent drives a cloud browser, while the Browser Use CLI and the Python library drive a cloud or local browser.

Benchmark plot

../hard_benchmark_v2.jpg is a lossless crop of the original plot. Only the top 80 pixels containing the title were removed; all retained pixels are unchanged. The title appears as a README heading instead.

Driving-test demo

The inline GIF is converted from Johannes Dittrich's public driving-test video. It preserves the full 20.4-second recording at 960×540, 10 frames per second, with an infinite loop. The source recording already obscures the contact fields. No demo footage was generated.

The GIF is hosted as a GitHub attachment so cloning the repository does not download the animation.