Finalist
RingZero
When thousands of people gather for large social events like huge festivals, pilgrimages, and religious gatherings, families get separated in the chaos.
Core trick
On-device Gemma structures a spoken description into searchable attributes, and phones sync over a local hotspot WebSocket relay with Hive persistence.
Description
When thousands of people gather for large social events like huge festivals, pilgrimages, and religious gatherings, families get separated in the chaos. Cell networks collapse from sheer congestion precisely when people need them most. A panicked parent searching for a lost child has no way to communicate, and centralized systems requiring internet connectivity and server infrastructure simply don't work when connectivity fails.
MELA solves this by turning any volunteer's phone into a fully functional lost-and-found station that works completely offline. A parent speaks in their own language, and the app powered by on-device Gemma 4 E2B AI converts their words into a structured record of what to look for. Rather than relying on centralized face-recognition databases, MELA uses voice descriptions and attribute matching, keeping the system privacy-first and accessible even when no photos exist. Multiple stations sync over a local phone hotspot using WebSocket relay, while Hive persistence ensures every card survives network failures and phone restarts. When another volunteer finds someone matching that description, they can verify the match right there without needing internet. The entire system is multilingual, privacy-first, and designed to coordinate hundreds of volunteers across a single gathering in the real world where connectivity is unreliable and speed matters.
README excerpt
# MELA 🪔 — Offline-First Lost & Found for India's Mega-Gatherings > *"Intelligence is always local. Connectivity is opportunistic."* Built at the **Google DeepMind Bangalore Hackathon · July 11, 2026** — the commit history is the build log. --- ## The Problem At Maha Kumbh 2025, **~54,000 people** — mostly women and elderly — were separated from their families. On the busiest bathing day alone, **8,725** people were reported missing. Cell networks collapse from congestion precisely on those peak days. The Bhule-Bhatke camp has reunited lost pilgrims with the same loudspeaker since **1946** (~15 lakh reunited, including 21,000+ children). MELA gives that loudspeaker a brain — one that fits in a volunteer's pocket. --- ## What MELA Does MELA turns any volunteer's phone into a fully functional lost-and-found station — **no internet required**. 1. 🎙️ **Lost-report intake** — A panicked parent speaks in Hindi. Gemma 4 E2B (running entirely on-device) converts unstructured speech into a structured card: age, clothing, name, last-seen location. 2. 🤖 **Agentic slot-filling** — If a field is missing, the app asks exactly **one follow-up question** aloud in Hindi: *"Kya usne chashma pehna tha?"* → card updates. Sense → decide → act → check: the model extracts, deterministic code decides what to ask. 3. 💾 **Restart-safe storage** — Cards, sync queue, and station identity are persisted locally (Hive). The app survives being killed or the phone rebooting mid-demo. 4. 📷 **Found-p