Ask a question about a place. Watch the map answer.

GeoSense Agent is an AI agent that calls machine-learning, deep-learning, LiDAR and street-view tools to answer plain-English questions about a location, while a 3D digital twin flies to the result. Built by Packiarajan Siva (M.Tech Geoinformatics, University of Madras).

Try it

Chat with the agent

The main demo: type a question and the agent chooses its tools.

Open the demo

3D digital twin

CesiumJS globe with flood zones, LiDAR buildings and Mapillary street view.

Open the twin

API playground

Call all 7 tools directly from the interactive Swagger page.

Open API docs
The site scales to zero to stay free, so the first request after a quiet period can take 10 to 30 seconds. The AI model runs on a free tier, so a burst of questions may briefly be rate-limited. Coverage: Chennai and Manhattan, NYC; land-cover classification covers Velachery only.

Questions to ask:

Architecture

Cloud deployment (Phase 5): three Cloud Run services in Singapore, a Neon PostGIS database, Gemini for the agent, Mapillary for street imagery.

GeoSense cloud architecture diagram

How it was built (Phases 1 to 4)

GeoSense phases 1 to 4 diagram

Tech

Python, FastAPI, Model Context Protocol, LangGraph, Gemini, Streamlit, PostGIS (Neon), scikit-learn / XGBoost / SHAP, PyTorch U-Net, LiDAR (PDAL, laspy), SegFormer, Mapillary, CesiumJS, Vite, Docker, Google Cloud Run, Cloud Build, Secret Manager, GitHub Actions.