Back to browse
GitHub Repository

AI persona-based behavioral testing for web apps. No test scripts. YAML-configured. Vision-powered.

0 starsPython

SpecterQA – AI personas test your web app, no scripts needed

by synctek·Feb 23, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainSolve My Problem

Vision-based E2E tests survive UI refactors, but Claude-per-run cost adds up fast.

Strengths
  • Persona-driven testing captures real user behavior variability (frustrated admin vs power user).
  • No selector maintenance means tests stay valid through CSS/markup changes that break Playwright/Selenium.
  • Clear cost transparency with per-run budgets ($0.30–$3.00) and step-by-step breakdowns.
Weaknesses
  • Claude vision API cost ($0.30–$3 per run) becomes expensive at scale vs free/cheap Selenium alternatives.
  • Relies entirely on Claude's ability to understand screenshots; hallucinations or misclicks aren't yet logged clearly.
Target Audience

QA engineers, full-stack developers building web apps, teams struggling with flaky E2E tests.

Similar To

Playwright · Cypress · Sauce Labs (cloud E2E)

Post Description

SpecterQA is an open-source CLI for behavioral testing. Instead of writing test scripts with selectors, you define personas (YAML) and journeys (goals). The engine launches a real browser via Playwright, screenshots the page, sends it to Claude's vision model, and the AI decides what to click/type/scroll. Loop until done or stuck.

The idea: test scripts break when markup changes. Vision-based tests break when the UX actually breaks.

Personas have attributes like technical comfort, patience, and role that shape navigation behavior. A "frustrated non-technical admin" navigates differently than a "power user developer."

pip install specterqa specterqa init specterqa run -p demo

Cost: ~$0.30-$3.00/run depending on journey length. Built-in budget caps. Requires Anthropic API key.

Previously called GhostQA — we rebranded after discovering ghostqa.com exists as an AI testing company. Clean break, no confusion.

GitHub: https://github.com/SyncTek-LLC/specterqa

MIT license. Alpha (v0.3.0). Feedback welcome.

Similar Projects

AI/ML●●Solid

BNNR – a closed-loop pipeline for improving vision models

XAI-driven model improvement loop, but Weights & Biases already tracks experiments better.

Big BrainNiche Gem
dominka
102mo ago