ARCHAI

ARCHAI is sovereign AI infrastructure for cultural heritage — a research toolkit that lets museums run their own semantic search, AI-grounded object conversations, spatial interpretation, accessibility support, and visitor engagement systems without cloud dependency or subscription costs.

Each object speaks in first person through prosopopoeia, grounded in verified institutional metadata with a five-layer hallucination prevention framework. Visitors interact via AUX.IO through NFC, QR, hyperlink, Bluetooth beacon, map, or location-aware exhibition trigger — and every AI response traces back to the collection record.

AUX.IO is also being developed as an accessibility layer for collections, with text-to-speech and speech-to-text pathways in progress so the interface can eventually speak and listen as well as display.

The data format powering each conversation is Obtext (Object Context) — a structured record containing identity, physical properties, temporal context, significance, and crucially, constraints — what the object explicitly does not know.

ARCHAI remains an active research prototype. This website is a public-facing demo layer rather than the full operational app. FAMTEC is open to funded research partnerships, institutional pilots, accessibility testing, collection-data collaborations, development support, and evaluation with museum, gallery, archive, and university teams, and looks forward to collaborating, growing, learning, researching, and testing with partners across the wider GLAM sector.

Developed as part of doctoral research at RMIT University, School of Design. Presented at ISEA2026 Dubai and the 6th Summit on New Media Art Archiving.