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
Share this project:

Updates