minori (実り)

AI-powered agricultural collaboration platform — Voice-first field recording with harvest prediction

Overview

minori (Japanese: 実り, meaning "harvest" or "fruition") is an AI-powered platform designed to help agricultural cooperatives manage crop production and supply chain coordination. It enables farmers to record field activities through voice and photos, while AI predicts harvest timing and yields.

Key Features

• 🎤 Voice Recording — Speak to record, accessible for elderly farmers
• 📷 Photo Recognition — Identify crops and growth stages from photos
• 🤖 AI Prediction — Predict harvest dates and yields based on climate data
• 📊 Supply-Demand Matching — Connect farmers with buyers through cooperatives
• 💬 LINE Integration — No additional app installation required

Philosophy

minori follows the AII (AI Interactive) design philosophy:

Interfaces should understand humans, not force humans to learn interfaces.

Farmers simply speak or take photos — AI understands and acts accordingly.

Quick Start

Prerequisites

• Bun >= 1.0

Installation

# Clone the repository
git clone git@github.com:RikaiDev/minori.git
cd minori

# Install dependencies
bun install

# Copy environment variables
cp .env.example .env
# Edit .env and fill in required API keys

Development

# Start development server
bun run dev

# Type checking
bun run typecheck

# Run tests
bun run test

# Lint
bun run lint

Project Structure

minori/
├── packages/
│   ├── shared/        # Shared types and utilities
│   ├── core/          # Core logic (prediction, crop database)
│   ├── ai-engine/     # AI engine (speech recognition, intent parsing)
│   └── line-bot/      # LINE Bot integration
├── apps/
│   └── api/           # API server
└── docs/              # Documentation

Architecture

┌─────────────────────────────────────────────────────────┐
│                    LINE Official Account                │
│              (Farmers / Cooperatives / Buyers)          │
└────────────────────────┬────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────┐
│                     AI Engine                           │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐     │
│  │   Whisper   │  │   Intent    │  │   Vision    │     │
│  │   (Speech)  │  │   Parser    │  │    (Photo)  │     │
│  └─────────────┘  └─────────────┘  └─────────────┘     │
└────────────────────────┬────────────────────────────────┘
                         │
                         ▼
┌─────────────────────────────────────────────────────────┐
│                      Core                               │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐     │
│  │    Crop     │  │   Harvest   │  │    Price    │     │
│  │  Database   │  │  Predictor  │  │   Analyzer  │     │
│  └─────────────┘  └─────────────┘  └─────────────┘     │
└─────────────────────────────────────────────────────────┘

Documentation

• API Reference — Endpoint documentation
• Architecture — System design and diagrams
• Contributing Guide — How to contribute
• Claude Guidelines — AI assistant coding standards

Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Workflow

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Community

• Issues — Bug reports and feature requests
• Discussions — Questions and ideas

License

This project is licensed under the MIT License — see the LICENSE file for details.

Acknowledgments

• OpenAI Whisper — Speech recognition
• LINE Messaging API — Chat platform
• Taiwan Central Weather Administration — Weather data