I built this as a personal open-source project to explore how EU AI Act
requirements can be translated into concrete, inspectable technical checks.
The core idea is local-first compliance: – risk classification (Articles 5–15, incl. prohibited use cases) – bias evaluation using CrowS-Pairs – automatic Annex IV–oriented PDF reports – no cloud services or external APIs (browser-based + Ollama)
I’m especially interested in feedback on whether this kind of technical framing of AI regulation makes sense in real-world projects.
loading...