Posture and stress are two critical factors that can significantly impact a person’s physical and mental wellbeing. A variety of physical and mental health problems can be avoided by maintaining proper posture and controlling stress. Chronic discomfort, decreased mobility, and an increased risk of musculoskeletal problems are all consequences of poor posture. Additionally, stress has negative impacts on physical and mental health, such as depression, anxiety, and cardiovascular disease. However, traditional methods of assessing posture and stress levels, such as physical examinations or self-reporting, can be subjective and time-consuming. Recent advances in machine learning and computer vision techniques have made it possible to develop models that can automatically detect posture and stress levels from video data. In this paper, a Django framework was developed to embed models for posture and stress detection. The system calculates angles between tracked distance vectors to determine whether the posture is good or bad. For stress assessment, the models analyze facial features and expressions. Human posture recognition using skeleton data is a key research area in human-computer interaction. To enhance posture recognition accuracy, skeleton data from the MSR 3D action dataset is utilized, which identifies 33 key skeletal points in the body. Additionally, stress detection based on facial features and emotions leverages convolutional neural networks. These advancements aim to provide more objective and efficient means of monitoring and improving posture and stress levels for better overall health outcomes.