#qa-automation

AI Testing Agent Framework · 16 experts + 32 skills + 49 utils · Multi-LLM (Claude/OpenAI/Qwen/etc) · MCP-native · Open-source · Learn-while-using

An open-source, multi-agent AI framework for Playwright test automation — featuring a 2D pixel-art office, live SSE telemetry, and Gemini / Ollama LLM routing.

All-in-one Developer Studio & Desktop GUI for Bubble.io (DevOps, Schema, Dead Code Audit, AI Translation, Visual QA)

An AI QA agent team designed, wrote, and maintains a 68-case regression suite against a live banking app — 4 confirmed defects found, Jira-ready tickets generated from evidence, zero silently-passing known bugs.

A platform-layer playbook for running QA with multiple AI Agents. Conventions, structures, and guardrails above your LLM/IDE.

AI-powered self-healing browser automation platform

AI Agent Infrastructure Platform using Hermes, Discord, DeepSeek, and WSL2 with architecture generation, research automation, and coding assistant capabilities.

Agentforce AI agent for automated UI testing of Salesforce orgs using Claude computer-use and Playwright

Autonomous UI/game-testing agent: vision-language reasoning, browser control, action planning, failure recovery, and evaluation.

AI-powered Quality Engineering Platform built with FastAPI, React, PostgreSQL, and Docker for requirement analysis, API test generation, and automation failure analysis.

A swarm of QA agents that battle-tests your app in a real browser. Every finding ships a screenshot, repro steps and a failing test.

Agentic E2E QA pipeline (user story to PR) with code-enforced guards against self-certifying agents

Agentický QA projekt: E2E testy e-shopu Toolshop v Playwright + TypeScript, řízené přes Claude Code s lidskou verifikací