AgriTech is an innovative AI-powered platform designed to empower farmers and agricultural communities with real-time insights, disease detection, and interactive collaboration tools to ensure a sustainable future.
- Clone:
git clone https://github.com/omroy07/AgriTech.git - Backend:
pip install -r requirements.txt && python src/backend/app.py - Frontend: Open
http://localhost:8000after running a local server insrc/frontend/. - Goal: Get accurate soil analysis and plant health reports instantly.
| Crop Recommendation | Disease Detection | Community Chat |
|---|---|---|
 |
 |
 |
- User Input: Farmers upload soil data or plant images via the Dashboard.
- Processing: The Flask backend routes data to specific AI/ML models.
- ML Inference:
- CNN Models: Detect plant diseases from images.
- Random Forest/XGBoost: Suggest crops based on soil NPK levels.
- Output: Results are displayed with preventive measures and yield predictions.
- 🌾 Crop Recommendation: AI suggestions based on soil and weather.
- 📉 Yield Prediction: Advanced models to forecast seasonal harvest.
- 🔬 Disease Prediction: Early detection of plant diseases with treatment steps.
- 🤝 Farmer Connection: A community hub to share resources and advice.
- 🛒 Shopkeeper Listings: Local directory for agricultural products.
- Frontend: HTML5, CSS3, JavaScript (ES6+)
- Backend: Flask (Python) / Node.js
- Machine Learning: TensorFlow, Scikit-Learn, OpenCV
- Database: MySQL / MongoDB
- DevOps: Docker, GitHub Actions (CI/CD)
AGRITECH/
├── 📁 src/
│ ├── 📁 frontend/ # UI logic: HTML, CSS, and Client-side JS
│ │ ├── 📁 pages/ # HTML files for Dashboard, Crop, & Disease pages
│ │ └── 📁 assets/ # Local icons and data samples
│ ├── 📁 backend/ # Flask API: Routes and Server-side logic
│ │ ├── app.py # Main entry point for the Backend
│ │ └── 📁 routes/ # Specific API endpoints (Crop, User, etc.)
│ └── 📁 ml_models/ # The "Brain" of AgriTech: AI/ML model files
│ ├── model.h5 # Pre-trained Deep Learning models
│ └── model.pkl # Pre-trained Scikit-Learn models
├── 📁 images/ # Screenshots, GIFs, and Logos used in README
├── 📄 requirements.txt # Python dependencies (Must install for ML)
└── 📄 README.md # Main Documentation
- Data Sanitization: All user-uploaded images are processed via OpenCV filters to ensure data integrity and prevent malicious file injections during the ML inference phase.
- Environment Safety: Sensitive information, including API keys, database credentials, and secret tokens, are strictly managed via
.envfiles to prevent accidental exposure in the version control system. - Model Validation: We implement continuous testing and cross-validation of our ML models (CNNs & Random Forest) to ensure a prediction accuracy threshold of 90% or above before deployment.
- Python 3.9+
- Node.js 18+
- Local Server (Live Server extension or Python
http.server)
git clone [https://github.com/omroy07/AgriTech.git](https://github.com/omroy07/AgriTech.git)
cd AgriTechcd src/backend
pip install -r requirements.txt
python app.pycd src/frontend
python -m http.server 8000
# The application will be live at http://localhost:8000- Cloud deployment
- Mobile app integration
- Real-time weather API
- AI chatbot for farmers
- Regional language support
Fork → Clone → Branch → Code → Commit → Push → Pull Request → Review → Merge
- Cloud Deployment: Migration to AWS/Heroku for global high-availability.
- Mobile Integration: Native Android application for on-field utility.
- IoT Support: Integration with real-time soil moisture and NPK sensors.
- Multilingual Support: Adding regional Indian languages to improve accessibility for farmers.
| Name | Role |
|---|---|
| Om Roy | Project Lead |
| Kanisha Ravindra Sharma | ML Engineer |
| Shubhangi Roy | ML Engineer |
We love contributions! Please read our CONTRIBUTING.md to get started with SWoC 2026 tasks. Whether it's fixing bugs, adding features, or improving documentation, your help is always welcome!
Made with ❤️ by the AgriTech Community. Part of SWoC 2026.
