Child malnutrition remains a critical worldwide health issue which prevents children from achieving proper physical development and mental growth and complete health from their earliest stages of life. The identification of health issues at their earliest stage requires immediate intervention to prevent future health complications. The research presents an AI-based Child Growth Monitoring and Malnutrition Prediction System which uses machine learning techniques to assess vital anthropometric metrics that include age height weight Body Mass Index (BMI) and Mid-Upper Arm Circumference (MUAC). We use a Random Forest classifier to correctly sort children into groups of normal, moderately malnourished, and severely malnourished. The system not only makes predictions, but it also has a nutrition recommendation module that looks at food nutrient data to suggest the best diet plans. The suggested system helps healthcare workers, daycare providers, and others by making it easier to diagnose problems early, lowering the risk of human error, and helping them.