Shared memory engine for Lore — three-tier storage, distillation, gradient context management
Compressing images using the BC1 (DXT1), BC2 (DXT3), BC3 (DXT5), BC4, BC5 & BC7 texture compression standard.
Classify GPU's based on their benchmark score in order to provide an adaptive experience.
Background Removal in the Browser
Compressing images using the Basis Universal Supercompressed GPU Texture Codec.
**GPU accelerated image resizer**
Compressing images using the ETC & ETC2 texture compression standard.
WebGL performance monitor that showing percentage of GPU/CPU load
ONNX Runtime Utilities for Unity
Easy to use npm NodeJS Monero Miner with C++, uses XMRIG for highspeed hashing.
ONNX Runtime Plugin for Unity
Minimal WebGPU shader library
Launch latest Chrome with the Devtools Protocol port open
Compressing images using the ASTC texture compression standard.
Primitives and SDK for LLM agent content workflows: compression, patching, progressive disclosure, signed URLs, collaborative document lifecycle, and retrieval planning
paddleocr models run on onnx
gpu-curtains is a 3D WebGPU rendering engine. It can be used as a standalone 3D engine, but also includes extra classes focused on mapping 3d objects to DOM elements; It allows users to synchronize values such as position, sizing, or scale between them.
A cross-platform OCR library based on PaddleOCR v5 and ONNX Runtime that is as small as possible.
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
Powerful, user-friendly voice activity detector (VAD) for the browser
⚡️ A React abstraction for the popular three-gpu-pathtracer.
Cornerstone3D Core
Typst symbol classifier
IDLE Protocol node — turn idle compute into revenue