AgriSaarthi AI

Upload a plant photo to detect possible diseases, pests, and health issues with AI.
Find nearby warehouses with real-time location, capacity, pricing, and storage details.
Centralized control to manage farmers, warehouses, schemes, services, and platform data.

About the Project

Inspiration

Agricultural services are often fragmented across soil laboratories, government schemes, markets, storage facilities, and advisory services. This makes it difficult for farmers to access reliable information and make timely decisions. AgriSaarthi AI was inspired by the need for a unified, farmer-centric digital platform that connects these services through intelligent assistance.

What We Built

AgriSaarthi AI is an AI-powered agricultural intermediary platform designed to provide personalized agricultural support through a single interface. It brings together crop and seed recommendations, soil intelligence, crop rotation, government-scheme discovery, market information, storage connectivity, and agricultural service access.

The platform also incorporates location-based discovery for nearby agricultural services and an AI-assisted plant health scanning workflow for identifying potential visible plant-health issues.

How We Built It

We developed the solution using a modular full-stack architecture. The frontend is built with React, TypeScript, Vite, and Tailwind CSS, while FastAPI and Python provide the backend and REST APIs. Supabase PostgreSQL, Authentication, and Storage support data management and secure application services. AI/ML capabilities use technologies including OpenCV, PIL, NumPy, and Scikit-learn, with Leaflet for interactive maps and Recharts for data visualization.

The core workflow is:

Farmer Query → Data Retrieval → AI Analysis → Personalized Recommendation → Service Connection

What We Learned

Developing AgriSaarthi AI helped us understand how AI, databases, APIs, geospatial services, and machine-learning components can be integrated into a practical agricultural ecosystem. We also gained experience in designing role-based systems and developing technology around real user needs rather than isolated features.

Challenges

The primary challenges were integrating multiple agricultural services into one platform, designing an interface accessible to farmers with different levels of digital literacy, handling location-based services, and ensuring that AI-generated recommendations are presented responsibly.

We also focused on maintaining a clear distinction between verified government information and application guidance, particularly where direct government API integration is unavailable.

Vision

Our vision is to create a scalable digital agricultural ecosystem that connects farmers, AI advisory services, soil laboratories, government services, markets, warehouses, buyers, and agricultural service providers through a single platform.

AgriSaarthi AI — One Platform. Connected Agriculture. Smarter Decisions.