Operate and verify web apps

Browser QA agent stack

A stack for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.

Built for Product and QA teams that want repeatable browser checks without writing every test from scratch.

Outcomes

  • Run web flows
  • Fill forms safely
  • Capture visual evidence
  • Report broken states

Workflow map

How the stack fits together

01

Navigate

Open the target app and move through the same path a user would follow.

02

Interact

Click, type, upload, and choose options with explicit state checks.

03

Assert

Verify DOM text, URLs, console errors, screenshots, and data changes.

04

Report

Return concise findings with reproduction steps and artifacts.

Recommended stack

Start with these skills

Ranked by workflow relevance, quality score, GitHub adoption, and maintenance freshness.

#1CrawleeExcellent · 100

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.

24K starsApache-2.0browser-automation
Compare
$ npx skills add apify/crawlee
#2SeleniumBaseExcellent · 100

SeleniumBase is a framework for UI Testing, Web Scraping, and Stealth. Passes every bot-detection test with CDP Mode, and extends Playwright.

13K starsMITtesting-qa
Compare
$ npx skills add seleniumbase/SeleniumBase
#3Browser UseExcellent · 100

Make AI agents interact with websites using natural language

101K starsMITweb-automation
Compare
$ npx skills add browser-use/browser-use
#4MidsceneExcellent · 100

AI-powered, vision-driven UI automation for every platform.

14K starsMITautomation
Compare
$ npx skills add web-infra-dev/midscene
#5BrowserlessExcellent · 100

Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.

13K starsUnknownbrowser-automation
Compare
$ npx skills add browserless/browserless
#6AI Goofish MonitorExcellent · 100

基于 Playwright 和AI实现的闲鱼多任务实时/定时监控与智能分析系统,配备了功能完善的后台管理UI。帮助用户从闲鱼海量商品中,找到心仪产品。

13K starsMITbrowser-automation
Compare
$ npx skills add Usagi-org/ai-goofish-monitor
#7Crawlee PythonExcellent · 100

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

9.2K starsApache-2.0browser-automation
Compare
$ npx skills add apify/crawlee-python
#8ArtilleryExcellent · 100

The complete load testing platform. Everything you need for production-grade load tests. Serverless & distributed. Load test with Playwright. Load test HTTP APIs, GraphQL, WebSocket, and more. Use any Node.js module.

9.0K starsMPL-2.0browser-automation
Compare
$ npx skills add artilleryio/artillery

Ideal for

  • - Signup flows
  • - Checkout smoke tests
  • - Dashboard QA
  • - Visual regression triage

Avoid when

  • - The flow requires bypassing platform controls
  • - The target site disallows automation