As there is a rapid growth in city traffic when compared to the previous days, it is necessary for the better and upgraded ways to manage it. Our project brings a comprehensive Traffic Detection and Management System Using Machine Learning in a full Artificial Intelligence (AI) system to detect and manage the traffic. It can track and separate different vehicles like cars, motorcycles, trucks, and buses as they move. We use the YOLOv8 model with DeepSORT to follow and name objects. This lets us watch live video to see what type of vehicle is passing by and how fast it’s going. This information is then plugged into a system that keeps an eye on traffic without needing people to do it. This helps to make the roads safer and also gets more drivers to follow the rules. A key outcome of this system is its interface is very easy to use which is created with PyQt5, that allows operators set and monitor the vehicle speed limits and see the counts of each type of vehicle. In this system, OpenCV is used for computer vision jobs and PyTorch is used for machine learning which makes it strong and able to adapt to different settings. The system acts as an alternative to the need for manual oversight offering a productive automatic way to handle traffic violations. By upgrading the old traffic control methods, this project helps make roads safer and controlled in better manner assisting the city planners and traffic authorities to create better urban transport networks that exist for long period of time.