Due to fragmented advisory systems, limited data access, and language barriers, smallholder farmers frequently face difficulties when choosing crops. Decisions are further complicated by the need for sustainable resource use and climate variability. In order to provide accurate, context-aware recommendations that increase productivity and sustainability, recent AI-driven crop recommendation systems integrate soil, weather, yield, and market data. These systems integrate data insights with agronomic knowledge through machine learning, ensemble models, and hybrid rule-based techniques. Conventional crop selection techniques frequently rely on local customs or experience, which might not always produce the best outcomes. This study offers an AI-based crop recommendation system that assists farmers in selecting appropriate crops based on soil and climate conditions in order to solve this issue. To choose the best crop for cultivation, the system examines critical factors like temperature, humidity, rainfall, soil pH, nitrogen (N), phosphorus (P), and potassium (K). The system was created using machine learning techniques, and an agricultural dataset was used to train several models, such as Random Forest, Decision Tree, and Support Vector Machine (SVM). The dataset was cleaned and made ready for analysis prior to training. Accuracy and confusion matrix analysis were used to assess these models\' performance, and the Random Forest model outperformed the other tested algorithms. A straightforward prediction interface was developed to make the system useful and user-friendly. Users can enter soil and environmental values and instantly receive crop recommendations. This system can help farmers make better farming decisions, increase crop productivity, and promote more sustainable and effective farming methods.\n\n