An agent that gives kagent eyes: it grabs a webcam photo and transforms it with Nano Banana and Veo3. It also ships an American Sign Language mode, so accessibility was part of the design rather than an afterthought.
For a starter track, a clear extension — give the agent a new input channel — is the right shape. Webcam in, generated image out, all in one visible chain, so it demonstrates itself in seconds rather than needing a pitch. The sign-language mode is the detail that lingers: accessibility usually arrives late in a feature list, and putting it in from the start says something about how the entry was built.
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).