The Problem
Urban crises cascade. A heat wave overloads the power grid → traffic lights fail → hospitals lose AC → emergency services gridlock → 200,000 people affected in 30 minutes.
SENTINEL predicts these chains and intervenes at the earliest point.
How It Works
Five autonomous AI agents coordinate in real-time:
| Agent | Role |
|---|---|
| WATCHER | Monitors live data from Singapore government APIs |
| PROPHET | Predicts cascade failures using graph algorithms |
| RESPONDER | Plans optimal interventions |
| GUARDIAN | Alerts and protects vulnerable populations |
| HEALER | Dispatches autonomous repair crews |
Quick Start
# Backend
cd sentinel
python -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
python -m uvicorn src.api.main:app --reload --port 8000
# Frontend (new terminal)
cd frontend-3d
npm install && npm run dev
Open http://localhost:5174
Data Sources
| Source | Data | Status |
|---|---|---|
| LTA DataMall | Real-time traffic incidents | Live |
| data.gov.sg | Weather, PSI, temperature | Live |
| Groq AI | Llama 3.3 70B analysis | Live |
All APIs are free tier. Zero deployment cost.
Tech Stack
- Frontend: React, TypeScript, deck.gl, Framer Motion
- Backend: Python, FastAPI
- AI: Groq (Llama 3.3 70B), LangGraph
- Data: NetworkX, Singapore Government APIs

Log in or sign up for Devpost to join the conversation.