“playwright”

Playwright testing best practices for Next.js applications (formerly test-playwright).

Automate real browsers from the terminal for navigation, forms, screenshots, extraction, and UI debugging using playwright-cli.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging)…

Playwright Tools.

Browser automation using Playwright with optional stealth mode to bypass anti-bot protection.

Diagnose and fix failing Playwright tests: traces, verified fixes, flaky/order verdicts, a11y audit.

Subagent "playwright-test-planner" from hyperdxio/hyperdx: Use this agent when you need to create comprehensive test plan for a web application or website

Subagent "playwright-test-generator" from hyperdxio/hyperdx: Use this agent when you need to create automated browser tests using Playwright Examples…

Subagent "playwright-test-healer" from hyperdxio/hyperdx: Use this agent when you need to debug and fix failing Playwright tests

Browser infrastructure for AI agents: stealth cloud browsers, an open-source Playwright-based framework and deployable functions.

Open-source SDK for browser agents that combines natural-language act, extract and observe with Playwright-style control.

Hosted browsers for Puppeteer, Playwright and Selenium scripts, with built-in unblocking and CAPTCHA solving.

Open-source browser agent in Python, plus a hosted cloud with stealth browsers and an agent API

Multi-agent framework for real-world task automation, built on CAMEL-AI and scored on the GAIA benchmark

Automates browser workflows on any website with vision-based LLM agents, via no-code app, SDK or API

Browser DevTools MCP

serkan-ozal

Playwright-powered browser automation and Node.js backend debugging for VS Code and Cursor via MCP.

Nova Act

amazonwebservices

AI-powered automation extension for IDE.

SessionLens: AI Agent Test Review

nikolaylosev

Review Claude Code, Codex and Cursor Agent sessions that write autotests: tests never run, weakened asserts, sleeps.

Browser infrastructure for AI agents: local and cloud Playwright-based browser sessions, scraping and deployable browser functions.

Gym-style Python environment for building and evaluating web agents on MiniWoB, WebArena, WorkArena and other benchmarks.

Stress test for realistic MCP use across Notion, GitHub, filesystem, PostgreSQL and Playwright servers.