FFmpeg builds for Windows on Arm - Qualcomm Snapdragon - ARM64

Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy.

Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.

Cross-platform Electron app for simultaneously streaming & recording microphone and speaker audio

Capture system audio output on macOS using Apple's Core Audio taps API.

Find suspicious (and possibly faked) GitHub stars at-scale

Capture system loopback audio on macOS 12.3+, Windows and Linux

Kernels & AI inference engine for phones

Digital Mind Extension

React Native binding of whisper.cpp.

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

On-device AI across mobile, embedded and edge for PyTorch

Web Interface for Cloudflare R2

The Fastest Way to Fine-Tune LLMs Locally

⚡ Extremely fast online playground for every programming language.

Fetch an entire site and save it as a text file (to be used with AI models).

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Create Node modules in Swift

Official inference framework for 1-bit LLMs

Devon: An open-source pair programmer

Embeddable stream processing engine based on Apache DataFusion

Issue API keys for your Supabase app with one line of SQL

Open source alternative to Auth0 / Firebase Auth / AWS Cognito

AdalFlow: The library to build & auto-optimize LLM applications.

Browser extension for AnythingLLM Docker & Desktop application

CloudFormation template that runs a 7 Days to Die server with idle shutdown, start/stop access control and static IP