Effective management of post-harvest paddy quality largely depends on maintaining optimal moisture levels to minimize spoilage and financial losses. Traditional methods of assessing moisture content are often unsuitable for real-time monitoring in field environments. This study presents a novel approach that combines Internet of Things (IoT) technology with Edge-AI analytics to automatically categorize paddy into three hydration states: Dry, Moist, and Wet. The proposed system employs an ESP32 microcontroller connected to a capacitive moisture sensor and environmental monitoring units for temperature and humidity. A key feature of the design is a context-aware algorithm that adjusts moisture classification based on real-time weather inputs, ensuring dependable performance under varying atmospheric conditions such as rainfall or high humidity. All collected data are transmitted to a cloud-based dashboard, enabling remote tracking and decision-making. This low-cost, intelligent framework provides farmers with instant insights into grain quality, supporting timely interventions that can substantially reduce post-harvest deterioration and improve overall storage outcomes.