GitHub Repository

QA Agent is an AI-powered E2E testing platform for product, QA, and engineering teams. It lets you define browser tests in natural language, execute them with an LLM-driven browser agent, and inspect screenshots, GIFs, and run history when something fails.

3 starsTypeScript

Run end-to-end browser tests using natural language

Name: Run end-to-end browser tests using natural language
Availability: InStock
Author: jimmypk

by jimmypk·Mar 8, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●MidShip It

Natural language E2E tests sound good until you need debugging or maintenance.

Strengths

•Real browser execution via browser-use avoids Playwright selector fragility — genuine UX.
•Multi-LLM provider support (Claude, GPT, Gemini) and real-time SSE streaming shows polish.
•Artifact capture (screenshots, GIFs, logs) is table stakes but well-implemented.

Weaknesses

•LLM flakiness in test execution is unstated — no mention of retry logic or determinism guarantees.
•'Chat with your codebase'-adjacent category already saturated; dozens of tools claim natural language automation.

Post Description

Similar Projects

Developer Tools●●Solid

AgenQA – Turn natural language into E2E web app tests using AI

Natural-language -> E2E tests plus a visual desktop app, cloud sync and an npm-installable CLI is a pragmatic combo that will appeal to teams tired of brittle scripts. Usability-focused reporting and a recorder-ish desktop experience are the clearest differentiators here; what I want to see next is concrete evidence about cross-browser reliability and how the AI handles flakiness and changing selectors.

Solve My ProblemSlick

aldovincenti

103mo ago

Developer Tools●●●Banger