Developer Tools●●●Banger
Agent-QA – natural-language E2E tests for apps built with coding agents
Agentic test runtime builds execution memory to heal flaky tests automatically.
Big BrainSlickZero to One
pranshuchittora
101mo ago
Back to browse
Open-Source Agentic QA Harness with Memory
by pranshuchittora·May 20, 2026·18 points·2 comments
AI Analysis
●●●BangerSolve My ProblemBig BrainShip It
Self-healing tests that remember UI changes so you stop fixing broken selectors.
Strengths
- •Execution memory curates observations to prevent agents from rediscovering navigation models on every run.
- •YAML-based natural language steps remove the friction of writing complex Puppeteer or Cypress code.
- •Cross-platform support handles both web browsers and mobile contexts from a single test definition.
Weaknesses
- •Relies heavily on LLM consistency; complex stateful flows might still hallucinate without strict guards.
- •Competes directly with established players like Playwright AI and Applitools that have deeper enterprise integration.
Category
Target Audience
QA engineers and frontend developers tired of maintaining brittle Selenium/Playwright scripts
Similar To
Playwright · Cypress · Rainforest QA
Post Description
GitHub - https://github.com/vostride/agent-qa
Live Demos - https://vostride.com/demo/agent-qa
Similar Projects
Developer Tools●●Solid
Agent-QA: Open-source AI end-to-end testing for web and mobile apps
Natural language E2E tests with execution memory, competing with Playwright and Cypress.
Solve My ProblemShip It
pranshuchittora
311mo ago
Developer Tools●●Solid
Upload test cases and get automated Playwright tests back
Replaces manual Playwright scripting, but Claude-generated tests and GitHub Copilot already cover this.
Ship ItSolve My Problem
ksurace
203mo ago
Developer Tools●Mid
Run end-to-end browser tests using natural language
Natural language E2E tests sound good until you need debugging or maintenance.
Ship It
jimmypk
103mo ago
Security●●Solid
Burrow – Runtime Security for AI Agents
Natural language policies block risky agent actions before they execute.
Solve My ProblemSlick
saranshrana
302mo ago
Developer Tools●Mid
RiddleRun – AI run end-to-end browser tests
AI E2E testing when Playwright, Cypress, and Testim already dominate.
Ship ItBold Bet
raffasch123
3010d ago