Zero-dependency browser automation CLI. 70+ commands, 10 test assertions, smart commands (click/fill by text — no LLM needed). MCP server for AI agents with 500x fewer tokens. Extract, observe, script runner. 50KB, pure CDP.

A powerful web scraping library built with Playwright that provides a declarative, step-by-step approach to web automation and data extraction.

Gives agents a real browser. URL in, pruned snapshot out. Replaces Playwright, Selenium, Puppeteer. Zero deps, zero wasted tokens.

AI-native browser automation for OpenClaw, LangChain, and AI agents. Automate job applications, price monitoring, trading bots, web scraping. Puppeteer/Selenium alternative with 40+ capabilities.

Chrome Automation & Browser Automation at the Engine Level

Dual-browser DevTools Protocol automation | 18 actions | Tab workers | MCP-native | Chrome + Comet

Node.js browser automation library with DrissionPage-style API. Built-in anti-detection, TypeScript support, connects to existing Chrome via CDP.

Screenshot every HTML element matching a CSS selector to its own PNG (1080×1440 default for 小红书 carousel)

MCP server that drives any Chromium-based browser (Chrome, Edge, Brave, Opera, Vivaldi, antidetect, headless) via the Chrome DevTools Protocol — no Puppeteer, no Playwright. Navigate, click, fill, screenshot, run JS, handle dialogs, click cross-origin iframes.

GitHub Action to take automated website screenshots. Visual regression testing, deployment verification, PR previews. No Puppeteer needed.

Official client SDKs for the Webshot screenshot API — capture any URL as PNG, JPG, WebP, or PDF. JavaScript/TypeScript, Python, PHP.

Server-side image generation API. Generate OG images, social cards, and email banners in 2ms — 500x faster than Puppeteer.