Norfair is a customizable lightweight Python library for real-time 2D object tracking. Using Norfair, you can add tracking capabilities to any detector with just a few lines of code. Features Any detector expressing its detections as a series of (x, y) coordinates can be used with Norfair. This includes detectors performing object detection, pose estimation, and instance segmentation. The function used to calculate the distance between tracked objects and detections is defined by the user, making the tracker extremely customizable. This function can make use of any extra information, such as appearance embeddings, which can heavily improve tracking performance. Modular. It can easily be inserted into complex video processing pipelines to add tracking to existing projects. At the same time it is possible to build a video inference loop from scratch using just Norfair and a detector. Fast. The only thing bounding inference speed will be the detection network feeding detections to Norfair. Norfair is built, used and maintained by Tryolabs.