Show HN: QAgent – a self-healing QA agent that fixes bugs and opens PRs

QAgent, a self-healing QA agent that automatically tests web applications, identifies bugs, applies fixes, and verifies fixes without human intervention, has been released as an open-source project on GitHub. The multi-agent system uses Browserbase and Stagehand for AI-powered browser automation, Redis as a vector knowledge base for learning from past bugs, and Vercel for instant deployment after fixes, with the goal of creating a closed-loop for automated bug detection and fixing.

A self-improving QA agent that automatically tests web applications, identifies bugs, applies fixes, and verifies the fixes – all without human intervention. QAgent is a multi-agent system that creates a closed-loop for automated bug detection and fixing: ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ TESTER │───▶│ TRIAGE │───▶│ FIXER │───▶│ VERIFIER │ │ Agent │ │ Agent │ │ Agent │ │ Agent │ └──────────┘ └──────────┘ └──────────┘ └──────────┘ │ │ │ ┌──────────────┐ │ │ │ Redis │◀────────────────┘ │ │ Knowledge │ │ │ Base │ │ └──────────────┘ │ │ ▼ ▼ ┌─────────────────────────────────────────────────────────┐ │ W&B Weave Observability │ └─────────────────────────────────────────────────────────┘ Continuous Testing : Runs E2E tests like a QA engineer, simulating real user flows Automatic Bug Fixing : Doesn't just report bugs – it fixes them and redeploys Self-Improvement : Learns from past bugs to diagnose and fix faster over time Measurable Impact : Track pass rates, time-to-fix, and iterations to prove improvement Clone the repository git clone https://github.com/rishabhcli/QAgent.git cd QAgent Install dependencies pnpm install Set up environment cp .env.example .env.local Edit .env.local with your API keys Run development server demo app pnpm dev Run the QAgent agent pnpm run agent Start the Marimo dashboard marimo run dashboard/app.py | Technology | Purpose | |---|---| Browserbase + Stagehand | AI-powered browser automation for E2E testing | Vercel | Instant deployment after fixes | Redis | Vector knowledge base for learning from past bugs | W&B Weave | Tracing and evaluation of agent runs | Custom Orchestrator ADK/A2A-compatible | Multi-agent workflow coordination ADK integration planned | Marimo | Interactive analytics dashboard | Next.js | Demo application | OpenAI | LLM for patch generation | | File | Purpose | |---|---| | TASKS.md /rishabhcli/QAgent/blob/main/TASKS.md docs/PRD.md /rishabhcli/QAgent/blob/main/docs/PRD.md docs/DESIGN.md /rishabhcli/QAgent/blob/main/docs/DESIGN.md docs/ARCHITECTURE.md /rishabhcli/QAgent/blob/main/docs/ARCHITECTURE.md prompts/ralph-loop.md /rishabhcli/QAgent/blob/main/prompts/ralph-loop.md QAgent/ ├── .claude/ │ └── skills/ Domain-specific knowledge modules │ ├── browserbase-stagehand/ │ ├── redis-vectorstore/ │ ├── vercel-deployment/ │ ├── wandb-weave/ │ ├── google-adk/ │ ├── marimo-dashboards/ │ └── qagent-agents/ ├── agents/ Agent implementations │ ├── tester/ │ ├── triage/ │ ├── fixer/ │ ├── verifier/ │ └── orchestrator/ ├── app/ Next.js demo app ├── dashboard/ Marimo analytics ├── docs/ Documentation ├── lib/ Shared libraries ├── prompts/ Workflow prompts └── tests/ Test suites Test - Tester Agent runs E2E tests using Browserbase/Stagehand Detect - Failures are captured with screenshots, DOM state, logs Diagnose - Triage Agent analyzes the failure and queries Redis for similar issues Fix - Fixer Agent generates a patch using LLM + past fix patterns Deploy - Verifier Agent applies the patch and deploys via Vercel Verify - Tests are re-run to confirm the fix works Learn - Successful fixes are stored in Redis for future reference Repeat - Loop continues until all tests pass Knowledge Base : Every bug and fix is stored with embeddings for semantic search Pattern Learning : Similar bugs are fixed faster using past solutions TraceTriage : Agent failures are analyzed to improve prompts and workflows RedTeam : Adversarial tests continuously harden the system Start every session by reading CLAUDE.md /rishabhcli/QAgent/blob/main/CLAUDE.md Check current work in TASKS.md /rishabhcli/QAgent/blob/main/TASKS.md Follow the Ralph Loop workflow for iterative development Load skills from .claude/skills/ as needed Install dependencies pnpm install Run demo app pnpm dev Run agent pnpm run agent Run tests pnpm test Run E2E tests pnpm run test:e2e Lint and format pnpm lint && pnpm format Build pnpm build See .env.example /rishabhcli/QAgent/blob/main/.env.example for required environment variables: BROWSERBASE API KEY - Browserbase API key OPENAI API KEY - OpenAI API key REDIS URL - Redis connection string VERCEL TOKEN - Vercel API token WANDB API KEY - Weights & Biases API key GOOGLE CLOUD PROJECT - Google Cloud project reserved for ADK/A2A integration See the Quick Start quick-start section above for setup instructions. Once running, connect a GitHub repository through the dashboard and start your first QAgent run. QAgent Paper https://arxiv.org/html/2502.02747v1 - Agentic patching framework Stagehand https://www.stagehand.dev/ - AI browser automation Browserbase https://browserbase.com/ - Cloud browsers W&B Weave https://wandb.ai/site/weave - LLM observability Google ADK https://cloud.google.com/agent-development-kit - Planned orchestration framework Marimo https://marimo.io/ - Reactive notebooks