webgpu
Liquid Glass for the Web .
Liquid DOM is a monorepo for WebGPU liquid-glass rendering, React bindings, Three.js integration, React Three Fiber integration, and the renderer-agnostic layout engine used by the higher-level APIs.
Related contents:
Beautiful, open source, WebGPU-based charting library.
ChartGPU is a TypeScript charting library built on WebGPU for smooth, interactive rendering—especially when you have lots of data.
JavaScript 3D Library.
The aim of the project is to create an easy to use, lightweight, cross-browser, general purpose 3D library. The current builds only include a WebGL renderer but WebGPU (experimental), SVG and CSS3D renderers are also available as addons.
Related contents:
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.
Your personal AI assistant living right inside the browser. Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine. It can read pages, click buttons, fill forms, run JavaScript, and answer questions about any site you visit.
WebGPU LLM Inference Engine. The open-source Three.js-based modern LLM Engine that runs in your browser via WebGPU compute.
Related contents:
An advanced WebGPU 3D Gaussian Splatting renderer for THREE.js
3D Gaussian splats in typed-array tables on the CPU and GPU, drawn by three.js's WebGPURenderer on WebGPU or its WebGL2 backend. This site has the example pages, the documentation and the sources.
Run the Moebius inpainting model in the browser.
Paint over a region of an image to replace it; the denoising loop runs locally on your GPU. The first run downloads ~1.27 GB of weights from Hugging Face (then browser-cached). A WebGPU-capable browser (recent Chrome or Safari) is required.
Related contents:
A Complete WebGPU Game Engine for Browser & Desktop Arcade Oriented.
ArcadeGPU is a high performance WebGPU game engine inspired by classic techniques that made retro games legendary.
Related contents:
Modular cross-runtime WebGPU library for shaders, 3D scenes, GPU tensors, neural networks, and math viz.
vgpu is a TypeScript library for WebGPU: typed shader imports, a tiny gpu-first API, and the same code running in the browser, headless Node, and your test suite.
Free AI models that run in the browser.
Free, open-source AI models that run in your browser.
Speech-to-text, background removal, OCR, translation, image generation and more as JavaScript modules. Nothing leaves the device.
Related contents:
Bandwidth & FLOPS Benchmarks.
A microbenchmark suite for WebGPU: it isolates and benchmarks a device's raw ceilings — memory bandwidth (read/write) and FLOPS (fp32, fp16, int8; scalar/vec4/mat4/matvec) — one operation at a time in the browser, plus fixed-work comparisons of shader techniques such as layouts, workgroup sizes, reductions, and atomic aggregation. It is not a full app or game benchmark.
Related contents:
ThreeJS + wgpu-matrix + TypeGPU for WebGPU on Reanimated Worklets.
WebGPU Worklets allow you to run react-native-wgpu, Three.js, wgpu-matrix, and TypeGPU libraries on Reanimated Worklets on the UI Thread. With that integration, you can run smooth 3D animations backed by WebGPU using the Reanimated API and enjoy seamless integration with the Gesture Handler.
High-Performance In-Browser LLM Inference Engine.
WebLLM is a high-performance in-browser LLM inference engine that brings language model inference directly onto web browsers with hardware acceleration. Everything runs inside the browser with no server support and is accelerated with WebGPU.
The design platform for shader magic. WebGPU components for React, Vue, Svelte, Solid, JS & Framer. Open-source WebGPU shader components & free design editor.
Join 16,000+ design engineers crafting shaders for the web with our open-source components and design editor.
Related contents:
Type-safe WebGPU toolkit. A modular and open-ended toolkit for WebGPU, with advanced type inference and the ability to write shaders in TypeScript.
TypeScript library that enhances the WebGPU API, allowing resource management in a type-safe, declarative way.
tiny LLMs, Q4, in your browser.
Run, benchmark, and compare Small Language Models (SLMs) directly in your browser with hardware-accelerated WebGPU — 100% private, zero server cost, zero accounts.