GPU Powered Neural Networks for every Browser
WebNN API polyfill
TypeScript types for WebNN
WebNN provider for browser-ai — hardware-accelerated inference
Training and Evaluation AI Model Recommendation Engine for WebNN
Cross-platform NPU (Neural Processing Unit) detection for JavaScript — Node.js + Browser (WebNN)
Convert ML models (.onnx, .tflite) into ready-to-run WebNN API JavaScript/TypeScript code
React Native WebNN
Headless client-side AI video-generation engine for the browser. Runs LCM / SD-Turbo diffusion on WebGPU or WebNN (onnxruntime-web), CLIP tokenization via @huggingface/transformers, Mamba SSM temporal coherence, and WebCodecs MP4 muxing. No React. For a r
A tflite delegate based on Web Neural Network API (WebNN API).
The jQuery of local AI — A unified API that abstracts browser AI runtime fragmentation (Native / WebNN / WebGPU / WASM)
Test for deliver TFLite WebNN external delegate WASM binary
Full embeddable AI Video Studio for React — <StudioPanel> drop-in that runs LCM / SD-Turbo diffusion on WebGPU/WebNN, conditioned on a Mamba SSM state for temporal coherence, and muxes MP4 via WebCodecs. React layer on top of the headless @seanhogg/builde
LiteRT.js package
Local Inference internal utils package to avoid boilerplate across codebases.
Lightweight, high-performance browser ML inference framework with native concurrency support
Fork of @diffusion-studio/vits-web for easier built-in PiperTTS use.
Web api for using VITS based models in the browser!
Fork of @diffusion-studio/vits-web for easier built-in PiperTTS use.
Lightweight, high-performance browser ML inference framework with native concurrency support
AI powered features on the web made easy
Zero-Cost, privacy-first, modular SLM & RAG framework for the browser. Run AI entirely on-device with no API keys and no data leaving the browser sandbox.
Fork of @mintplex-labs/piper-tts-web for easier built-in PiperTTS use.
Fork of @diffusion-studio/vits-web for easier built-in PiperTTS use.
Simple DSL for WebNN graphs
Shared utilities for ONNX <-> WebNN conversion (types, op names, attrs, tensor data, etc.)
W3C WebNN implementation with ONNX, CoreML, and TensorRT backends [DO NOT USE IN PRODUCTION - Development Release]
Mobile deployment support for TrustformeRS (iOS, Android)