metadata
title: Argusic
colorFrom: gray
colorTo: yellow
sdk: static
pinned: false
Argusic
A hundred eyes on the market.
The independent benchmark that measures which AI coding agents can make real software run.
What we do
Argusic agents install, launch, debug and verify real open source software on a clean machine, with no human help. Every project gets a verdict backed by logs and a terminal recording. The rules are public: methodology.
Explore
Dataset: does-it-run
Every tested project with its verdict, score and pinned environment. Open data, CC BY 4.0, updated daily.
Source repository: GitHub
Per-project files, failure patterns and the same table as data.
A verification state on every row, plus Argusic's own measured spin-up times.
Pick a machine by RAM, CPU, screen and weight.