ResQNet AI is a production-ready tactical operations center (EOC) and Emergency Intelligence Platform designed to support emergency managers and responders during disasters.
ResQNet AI utilizes a decoupled reactive architecture:
- Frontend: React 18, TypeScript, Zustand state management, Tailwind CSS, Leaflet.js maps, and Framer Motion micro-interactions.
- Backend: FastAPI (Python), WebSockets, and asynchronous task workers.
- AI Engine: Graph-based Multi-Agent Orchestrator interfacing with LM Studio (local Gemma-4 model) or cloud OpenAI-compatible APIs with automatic circuit breaker fallbacks.
- Database: MongoDB Atlas with geospatial
2dsphereindexes for proximity routing.
- Python 3.10+
- Node.js 18+ & npm
- MongoDB (Local instance or MongoDB Atlas Connection URI)
- Navigate to the backend directory:
cd backend - Create a virtual environment and activate it:
python -m venv venv # On Windows (PowerShell) .\venv\Scripts\Activate.ps1 # On macOS/Linux source venv/bin/activate
- Install dependencies:
pip install -r requirements.txt
- Configure your environment variables. Copy
.env.exampleto.envand fill in your custom values:cp .env.example .env
- Seed the database with 300+ mock incidents, resources, shelters, and stations:
python seed.py
- Run the FastAPI development server:
uvicorn app.main:app --reload --port 8000
- Navigate to the frontend directory:
cd frontend - Install npm packages:
npm install
- Launch the Vite dev server:
npm run dev
- Access the EOC UI by opening http://localhost:5173 in your browser.
To build and run all services (MongoDB, Backend API, and React Frontend) together:
docker-compose up --build- Frontend will be accessible at
http://localhost:5173 - Backend API will run on
http://localhost:8000