✅ Update queued — the AI is re-ranking this list. The page will refresh shortly.
This page is already up to date.
ConvNetJS is an open-source JavaScript library for building and training convolutional neural networks and other neural-network models in the browser. It targets developers and researchers who want a lightweight, dependency-free environment for experimenting with neural networks client-side.
💡 Pick it for a maintained ConvNetJS successor with modern acceleration, pretrained models, and production deployment options.
A library for machine learning in JavaScript, with the capability of training and deploying models in the browser or on Node.js.
Microsoft
💡 Pick it when you need fast, portable browser inference from models trained in other ecosystems.
ONNX Runtime is an open-source cross-platform engine for running machine-learning models represented in ONNX format. It is aimed primarily at developers who...
Free, open source
Hugging Face
💡 Pick it for modern pretrained NLP, vision, and audio models running locally in JavaScript.
Transformers.js runs transformer models directly in browsers and JavaScript runtimes using technologies such as WebGPU and ONNX Runtime. It is aimed at...
Free and open source; model hosting or compute costs may apply
💡 Pick it for a simpler JavaScript API when your models are small and educational or application-focused.
A flexible library for building neural networks in JavaScript.
💡 Pick it for beginner-friendly browser experiments involving images, audio, pose, or interactive media.
ML5.js is a friendly machine learning library for the web that aims to make machine learning approachable for a broad audience of...
💡 Pick it when you need custom GPU kernels rather than a full deep-learning framework.
A JavaScript Acceleration library for GPGPU (General purpose computing on GPUs) in the browser and Node.js.
Your feedback helps us improve the AI rankings.
✅ Thanks for your feedback!
Suggest a product and our AI will verify it's a real alternative to ConvNetJS before adding it to the list.
