TensorFlow.js is a library for machine learning in JavaScript
Develop ML models in JavaScript, and use ML directly in the browser or in Node.js.
How it works
Run existing models
Use off-the-shelf JavaScript models or convert Python TensorFlow models to run in the browser or under Node.js.
Retrain existing models
Retrain pre-existing ML models using your own data.
Develop ML with JavaScript
Build and train models directly in JavaScript using flexible and intuitive APIs.
Demos

InSpace is a communication and virtual learning platform that gives people the ability to interact, collaborate, and educate in familiar physical ways. Learn how they used ML to prevent users from sending and receiving toxic messages.

See six exciting new demos pushing the boundaries of on-device machine learning in JavaScript. Share your work with #MadewithTFJS for a chance to be featured at the next Show & Tell, and check out our YouTube channel for more community showcases.

Discover how to achieve superpowers in the browser and beyond by embracing machine learning in JavaScript using TensorFlow.js in this speedy 30 minute talk by Jason Mayes.

We are happy to announce a new SIG to drive community ownership of TensorFlow.js projects. We encourage any developers working at the intersection of machine learning and web/JS applications to join and participate in the activities of the SIG.