@browser-use

cdp wraps the chrome devtools protocol in a persistent http server and typed javascript sdk, letting agents run browser automation snippets via cli without managing sessions.

browser-use automates web interactions via CLI with persistent sessions, supporting headless and real Chrome modes plus cloud browsers. covers navigation, inspection, clicking, form input, screenshots, and data extraction with ~50ms command latency.

open-source documents the browser-use python library with a reference index linking to external markdown files, covering agent, browser, and tool configuration. lacks actionable procedures and specific trigger guidance.

Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel,…

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud…

Controls a local browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web…

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.