#106106th of 118 in Agent frameworks and SDKs
skills
Browser automation skill that gives coding agents stealth and local Chrome control
- Stars
- 6.3k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
458 on 21 Apr 20266,342 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
BrowserAct Skills adds a `browser-act` CLI and Skill that agents such as Claude Code, Cursor and Codex load to drive a real browser. It supports local Chrome profile reuse and stealth browsers with fingerprint and proxy handling, and exposes indexed page state (`state`, `click 3`, `input 2`). It also offers CAPTCHA solving, human handoff via `remote-assist`, and Skill Forge, which generates site-specific scraping Skills.
Who it is for: Developers giving coding agents a real browser for scraping and logins
Strengths
- Indexed text page state lets agents click and type by number, without parsing the DOM
- Three browser modes: local Chrome, stealth privacy, and stealth fixed identity
- Sensitive actions like browser creation and proxy changes need fresh user approval, enforced in the Skill
- Works with any agent that can run shell commands and load Skills; Windows, macOS, Linux
Weaknesses
- Stealth browsers, solve-captcha and remote-assist require a BrowserAct login
- Managed proxies and more than 5 stealth browsers are paid
- Anti-bot and CAPTCHA features depend on BrowserAct's hosted services, not only local code
- Cloud scraping-Bot mode is a commercial product, separate from the MIT-licensed Skills
What it needs
- no GPU
- Needs Chrome, BrowserAct account (for stealth features), AI agent that can run shell commands
Quick answers
Is skills open source?
Yes. Its code is on GitHub under the MIT license.
Does skills need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |