The rapid global population growth, combined with increasing environmental challenges such as drought, necessitates the adoption of sustainable agricultural practices. This paper introduces GreenGrowth, a comprehensive framework designed to optimize irrigation and crop management through the integration of smart technologies. Using Internet of Things (IoT) devices and machine learning algorithms, GreenGrowth gathers real-time meteorological and soil data to accurately predict irrigation needs and recommend optimal crop types. The framework’s architecture includes a wireless sensor network, an ESP8266 microcontroller, and Firebase for data storage, enabling precise, data-driven decision-making. Key findings indicate that decision tree algorithms, outperform other models in predicting irrigation needs, while achieving a high accuracy rate in crop prediction. The implications of this research are significant for enhancing agricultural productivity, conserving water resources, and reducing manual intervention, thereby contributing to sustainable farming practices. This study not only demonstrates the feasibility of smart irrigation systems but also sets a foundation for future developments in data-driven agriculture.