# SnapCade

- **Event:** [Google I/O Hackathon](https://cerebralvalley.ai/e/google-io-hackathon)
- **When:** Sat, May 23 at 9:00 AM – 10:00 PM (PDT)
- **Where:** Shack15, San Francisco, CA
- **Team:** [Ashish Mukharji](https://cerebralvalley.ai/u/intabyu), [Sumeet Pardeshi](https://cerebralvalley.ai/u/sumeetpardeshi), [James Liu](https://cerebralvalley.ai/u/jamesliu)
- **GitHub:** https://github.com/sumeetpardeshi/hangout
- **Demo video:** https://youtu.be/arxVm1AZqO0
- **Gallery:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/60

This project is a full-stack React/Vite app that turns group selfies into a personalized browser arcade game: users capture or upload photos, optionally share geolocation, and the Express backend streams a four-agent Gemini 3.5 Flash pipeline that detects people, props, facial boxes, clothing, colors, and setting; generates custom SVG bobblehead avatars and a contextual backdrop; chooses one of several game templates; and assembles a playable game configuration. The frontend guides users through landing, camera capture, live AI analysis, reveal, and gameplay stages, crops participant faces client-side, persists sessions and UI preferences in localStorage, and renders the final game in an HTML5 canvas with switchable avatar styles, synthesized audio, score tracking, powerups, hazards, leaderboards, and multiple mechanics such as falling-item collection, side-scroller jumping, maze play, and shooter-style action.

---

Markdown version of https://cerebralvalley.ai/e/google-io-hackathon/hackathon/gallery/60. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt