JS to WebAssembly toolchain

Tokenizes Chinese texts into words.

2x faster than JSON.stringify()

Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight

Utilities to use the Hugging Face Hub API

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Run modern deep learning models in the browser.

The simplest way to run LLaMA on your local machine

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Lord of Large Language Models Web User Interface

SemanticFinder - frontend-only live semantic search with transformers.js

Waveform generation from audio file

Tensorflow Node.js Examples

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Deep learning models Serving with Python

High-performance In-browser LLM Inference Engine

Add local LLMs to your Web or Electron apps! Powered by Rust + WebGPU

hnswlib-node provides Node.js bindings for Hnswlib

hnswlib-wasm attempts to create a browser friendly version of hnswlib

Believe in AI democratization. llama for nodejs backed by llama-rs, llama.cpp and rwkv.cpp, work locally on your laptop CPU. support llama/alpaca/gpt4all/vicuna/rwkv model.

Tensor computation with WebGPU acceleration

JS port and JS/WASM bindings for openai/tiktoken

Online playground for OpenAPI tokenizers

Comlink makes WebWorkers enjoyable.

Browser-compatible JS library for running language models

WebGPU for Node [Deprecated, Unmaintained]