OVER\21551
f801621f06
- commands.md: add proxy management command group, --static-proxy options for browser create/update/stealth-extract - anti-blocking.md: split proxy section into three modes (dynamic/static/custom), document managed static proxy and stealth-extract usage - browser-modes.md: switch fixed-identity examples to --static-proxy, drop "coming soon" note, add static_proxy field to data model Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
BrowserAct Documentation
Browser automation CLI built for AI agents. Get past anti-bot walls, hand off to humans across platforms when stuck, run parallel tasks without cross-contamination, and isolate multiple accounts in independent browsers.
Getting Started
- Installation — Agent integration or manual install
- Quick Start — 60 seconds to first result
Features
- Anti-Blocking — Three-layer system: environment-layer emulation / execution-layer auto-resolution / human-layer remote handoff
- Better Headless — Default headless without disturbing, stealth headless undetected, no need to switch to headed when humans are needed
- Remote Assist — One command to hand off to a human, any device takes over via the link, agent resumes seamlessly when done
- Browser Modes — chrome (reuse local login), stealth privacy (frictionless batch scraping), stealth fixed identity (multi-account uncorrelated)
- Concurrency & Isolation — Independent identity across browsers, multi-session workspaces within a browser, zero residue in privacy mode
- Agent Design — Compact text output, indexed interaction, desc semantic memory, 50+ complete automation commands, secure by default
Your Personal Scraping Engineer
- Skill Forge — Explore once, generate a deploy-ready Skill, run the same stable path repeatedly — let AI write your scrapers