# 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](installation.md) — Agent integration or manual install
- [Quick Start](quick-start.md) — 60 seconds to first result

## Features

- [Anti-Blocking](anti-blocking.md) — Three-layer system: environment-layer emulation / execution-layer auto-resolution / human-layer remote handoff
- [Better Headless](headless.md) — Default headless without disturbing, stealth headless undetected, no need to switch to headed when humans are needed
- [Remote Assist](remote-assist.md) — One command to hand off to a human, any device takes over via the link, agent resumes seamlessly when done
- [Browser Modes](browser-modes.md) — chrome (reuse local login), stealth privacy (frictionless batch scraping), stealth fixed identity (multi-account uncorrelated)
- [Concurrency & Isolation](concurrency.md) — Independent identity across browsers, multi-session workspaces within a browser, zero residue in privacy mode
- [Agent Design](agent-design.md) — Compact text output, indexed interaction, desc semantic memory, 50+ complete automation commands, secure by default

## Your Personal Scraping Engineer

- [Skill Forge](skill-forge.md) — Explore once, generate a deploy-ready Skill, run the same stable path repeatedly — let AI write your scrapers

## Integration & Reference

- [Skills](skills.md) — Entry Skill + get-skills mechanism
- [Commands](commands.md) — Complete command reference