Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.
100
Quality
100
Trust
65
Fit
web-automationJun 11, 2026 pushMIT
$ npx skills add browser-act/skills
Evaluation
How to choose the right skill.
Waits for actual page state instead of fixed sleeps
Captures screenshots, DOM checks, or test evidence
Avoids external side effects without approval
Documents credential and session handling clearly
Questions
When should an agent use browser automation?
Use browser automation when the task requires real UI state, logged-in context, screenshots, or form flows that are not available through an API.
What is the main risk?
The main risk is uncontrolled side effects. Good skills include confirmation gates, verification steps, and clear boundaries around account changes or purchases.