Support for Armbian in Amlogic, Rockchip and Allwinner boxes. Support a311d, s922x, s905x3, s905x2, s912, s905d, s905x, s905w, s905, s905l, rk3588, rk3568, rk3399, rk3328, h6, etc.

An engine to run your pipelines in containers

Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild

Linux multi-touch gesture recognizer

The Kernel of CharlotteOS

SYCL implementation of Fused MLPs for Intel GPUs

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Tesseract Open Source OCR Engine (main repository)

🧠 Web Neural Network API

This sample shows how to implement a llama-based model with OpenVINO runtime

High-level bindings for wasi-nn system calls

fast state-of-the-art speech models and a runtime that runs anywhere 💥

Async Rust library for OpenAI on WASM

WebAssembly Micro Runtime (WAMR)

A Chrome extension to build a random playlist out of the user library

A from-scratch experimental AOT JS engine, written in JS

Purpose-built, Rust-native software engine for robotics

Run PyTorch LLMs locally on servers, desktop and mobile

A WASI shim for in the browser

Tracking WebAssembly proposals

NGINX Unit - universal web app server - a lightweight and versatile open source server that simplifies the application stack by natively executing application code across eight different programmin…

Spectacular AI SDK examples

Spectacular AI SDK

Agentic components of the Llama Stack APIs

Samples for Azure Kinect, Azure Kinect Body Tracking

The framework for building with WebAssembly (wasm). Easily load wasm modules, move data, call functions, and build extensible apps.

Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.