Tracking.js is an open-source JavaScript library that brings computer vision algorithms into the browser, enabling real-time face detection, color tracking, and object tracking directly on a web page. With more than 9,400 stars on GitHub, it is one of the best-known libraries for doing lightweight vision work client-side with HTML5 and a webcam, with repository activity continuing into 2026.
The tracking.js library brings different computer vision algorithms and techniques into the browser environment. By using modern HTML5 specifications, it enables real-time color tracking, face detection, and much more, all with a lightweight core of around 7 KB and an intuitive event-based interface. Developers subscribe to track events and receive coordinates as targets move through the camera feed or video element. Because everything runs locally in the browser, there is no server round-trip, no per-request API cost, and no video data leaving the user’s device, which makes it attractive for interactive installations and privacy-sensitive demos. The project provides documentation and API references on its website, and it can be installed through npm or Bower or simply included as a script.
Tracking.js is free and open source. There are no licenses to buy, no cloud bills, and no usage limits: include the library in your project and it runs on your visitors’ machines. The official documentation and examples are free too.
Tracking.js is aimed at web developers building interactive experiences: augmented-reality style page effects, gesture or face-driven interfaces, educational computer-vision demos, and prototypes that need quick in-browser detection without standing up a vision backend or paying for a cloud vision API.