BrowserAct Skills

BrowserAct is a browser automation CLI built for AI agents. It gets past anti-bot walls, hands off to humans across platforms when stuck, runs parallel tasks without cross-contamination, and isolates multiple accounts in independent browsers.

Use Cases

• AI agents need to perform browser automation (scraping, form filling, data extraction)
• Bypass anti-bot mechanisms to extract protected page content
• Run multiple browser tasks in parallel without interference
• Seamlessly hand over to a human operator across platforms when the agent is stuck
• Optimize interaction for LLM reasoning rather than traditional scripts

Core Capabilities

1. Three-Layer Block Breaking

1. Environment layer — stealth fingerprint spoofing, TLS rotation, proxy switching. The vast majority of blocks never trigger.
2. Execution layer — solve-captcha auto-solves CAPTCHAs; stealth-extract pulls protected pages in one command.
3. Human layer — remote-assist generates a live URL; the user takes over from any device, and the agent continues seamlessly when done.

2. Three Browser Modes

3. Zero-Interference Concurrency

• Cross-browser parallel — independent cookies, fingerprints, proxies. Sites cannot correlate them.
• Same-browser multi-session — shared login state, independent execution, tasks do not block each other.
• Privacy mode — fresh fingerprint and empty profile per session, zero residue when done.

4. Designed for Agent Reasoning

• Compact text output — indexed text format, several times more token-efficient than JSON or HTML.
• Indexed interaction — state returns an indexed list; click 3 / input 2 "...". No DOM parsing required.
• Semantic memory — every browser carries a desc, matched to tasks by meaning.
• Concurrency-safe — session ownership + explicit naming. Multi-agent operation never conflicts.

Security: Confirmation Gating

Sensitive operations (browser create/delete, profile import, proxy changes, security and privacy toggles) require explicit user approval. Prior approvals do not carry over. Enforced at the Skill layer, not a configuration toggle.

And More

• Better headless — default headless without disrupting users; stealth headless that is not detected.
• Cross-platform remote handoff — any device opens the link to take over, and the agent continues seamlessly.

Quick Start

# Extract protected page content (zero config)
browser-act stealth-extract https://example.com

# Full browser automation
browser-act --session my-task browser open <id> https://example.com
browser-act --session my-task state          # See clickable elements
browser-act --session my-task click 3        # Click by index
browser-act --session my-task input 2 "hi"   # Type into a field

The agent runs get-skills at the start of each session — gets environment state, browser list, and commands in one call:

browser-act get-skills core --skill-version 2.0.2

More examples and workflows →

Compatibility

OS: Windows, macOS, Linux

Agents: Claude Code · Cursor · VS Code · OpenCode · OpenClaw · Codex · Gemini CLI — works with any agent that can execute shell commands and load Skills.

What's Free

Almost everything is free. Only two features require payment: managed proxies (Dynamic/Static), and stealth browsers beyond the first 5.

Documentation

Full documentation covers anti-blocking, browser modes, sessions and concurrency, headless and remote handoff, agent design, the Skills system, and the complete command reference.

Read the full documentation →