Minimizing crop loss and guaranteeing food security depend on the early diagnosis of plant diseases. This paper proposes a novel Internet of Things (IoT)-based plant monitoring system with real-time disease detection capability. The system integrates hardware sensors for environmental monitoring (temperature, humidity, soil moisture, light intensity) with image capturing cameras. Microcontrollers process sensor data and transmit it to a cloud-based software platform. The software utilizes machine learning algorithms to analyze sensor data and capture plant images. These algorithms are trained on a robust dataset of healthy and diseased plant samples to identify potential disease outbreaks. Upon detection, the system generates real-time alerts and recommends specific treatment or preventive measures tailored to the identified disease. This system offers numerous advantages. Firstly, real-time data analysis allows for immediate intervention, preventing disease progression and minimizing crop damage. Secondly, the system leverages machine learning for accurate and reliable disease detection. Finally, the system is designed for cost-effectiveness and user-friendliness, promoting widespread adoption (Garg et al. in Slider-crank four-bar mechanism-based ornithopter: design and simulation. Springer Nature Singapore, Singapore, pp 267–280, 2022, [1].). Developing highly accurate and adaptable machine learning algorithms for diverse plant species and disease types remains a key challenge. Future research will focus on continuously improving the algorithm’s accuracy through ongoing data collection and model refinement. A viable future path is also investigating integration with automatic watering systems based on real-time soil moisture data.