Note: I built this entire application in 24 hours at runtime during a hackathon! If you liked it or found it helpful, please consider giving the repository a ⭐.
KrishiAI is an intelligent platform designed to empower farmers. It provides an AI-driven interface for voice consultations, on-device (offline) crop disease detection, and a real-time scraping interface for keeping up with the latest Government Schemes.
- Voice Consultation: Interactive voice interface (built with ElevenLabs & LiveKit) tailored for agricultural queries.
- Offline AI Crop Detection: 100% offline crop detection running directly in the browser via Web Workers (
@xenova/transformers). - Scheme Advisor: Live scraping and advisory interface for the latest Government Agricultural Schemes.
- Dynamic Monitoring: Dashboards to monitor chat and visually track real-time agent operations.
- Framework: Next.js (App Router)
- Language: TypeScript
- Styling: Tailwind CSS
- AI/Realtime Tools:
@elevenlabs/react,livekit-client,@xenova/transformers
- Node.js (version >= 20 and < 23)
- npm (or yarn/pnpm)
-
Clone the repository:
git clone https://github.com/your-username/KrishiAI.git cd KrishiAI -
Install dependencies:
npm install
-
Set up Environment Variables: Create a
.env.localfile in the root directory and add your required API keys (such as keys for Gemini, ElevenLabs, LiveKit, etc.). -
Run the development server:
npm run dev
-
Open the App: Open http://localhost:3000 in your browser to see the result.
Contributions, issues, and feature requests are welcome!
This project is licensed under the MIT License.