WebNN
WebNN describes an API for making machine learning available in web applications.
About WebNN
WebNN describes a web standard for running deep neural networks in web applications using on-device hardware such as GPUs, CPUs, or dedicated AI accelerators. It connects web apps and frameworks to native operating system machine learning services.
The site outlines in-browser inference with local media sources, on-device processing, use after initial asset caching without a network connection, and client-side computing without server farms. It lists ONNX Runtime Web, Transformers.js, and LiteRT.js as related frameworks.
Key features
- Run deep neural networks using on-device GPUs, CPUs, or AI accelerators
- Run inference in the browser with local media sources
- Process data on-device rather than on remote servers
- Continue working offline after initial asset caching
- Use native operating system services for machine learning
- Work with ONNX Runtime Web, Transformers.js, and LiteRT.js
- Uses client hardware such as GPUs, CPUs, and AI accelerators
- Operates offline after initial assets are cached
- Reduces need for server-side computing by using client devices
WebNN at a glance
- Category
- Development › Web Development
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Popular in Web Development
Well-known listings from the same topic.
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.