HN Showcase
Back to browse
Comber explores your app once, then replays QA checks deterministically

Comber explores your app once, then replays QA checks deterministically

by RADLAB·Jul 28, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●BangerShip ItBig Brain

No test scripts needed — it explores your app and catches what you forgot to test.

Strengths
  • •DOM-first exploration with vision fallback keeps costs at cents per run
  • •Generates exact repro steps, screenshots, and traces for every failure
  • •Deterministic replays mean expensive crawl happens once, cheap replays forever
Weaknesses
  • •Requires Anthropic or OpenAI API key for vision capabilities
  • •May miss edge cases that require specific user input or authentication flows
Target Audience

Frontend developers and QA engineers

Similar To

Playwright · Cypress · Percy

Similar Projects

Developer Tools●●Solid

Agent Audit Kit v0.1 – deterministic replay + stress for LLM agents

Deterministic capture + replay for LLM agents is a practical, under-served problem and this repo actually ships a 'golden run' zip with cold‑run verification hashes — that’s the kind of evidence chain auditors want. The focus on portable evidence bundles and stress verification suggests useful forensics and load testing of agent logic, but the release page looks early-stage; I'd like to see integrations (tooling for popular agent frameworks), richer docs, and example pipelines before I'd evangelize it.

Niche GemSolve My ProblemShip It
helpfuldolphin
105mo ago