A Kubernetes-native, multi-cluster inventory controller for enterprise AI infrastructure, extending the agentregistry idea so teams can actually see what agent infrastructure they are running at scale.
With a track literally called Explore agentregistry, the question was not whether you used it but whether you took it somewhere. This entry rebuilds the idea as a Kubernetes-native controller that can count assets across multiple clusters. The pain is unglamorous but real: the more agent infrastructure an organisation accumulates, the less anyone knows what is running where. Extending the sponsor's own project at enterprise scale is what a track like this rewards.
See all winners of Hackathon for MCP & AI Agents (Solo.io) →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).