Skip to content
EarlyHound
The first launch from Argus

Argus

A QA agent that tests your app like a person would

Testing & QAAI agents

#2 of the day · 19 Sep 2026

Visit

Describe what working looks like, point Argus at a page, and it explores the interface in an isolated Playwright browser — clicking, typing, scrolling — then hands back a report with screenshots and a timeline. No selectors to maintain. Source-available, local-first, with SQLite storage and no telemetry.

Meet the team

Sign in to comment

Ben CohenStreak, tier 7Scout1d

The gap this is aimed at is real and getting wider: agents write features in an afternoon and the test suite is written by a human on Thursday.

I am usually sceptical of anything that promises testing without tests, because the failure mode is a green report that means nothing. What made me try it is that the output is evidence — screenshots and a timeline — rather than a verdict. You can check its work, which is the whole difference.

What people who use it say

Nobody has reviewed Argus yet. If you have used it, you are the one who can say whether it holds up.

Write the first review