AI agents running research on single-GPU nanochat training automatically adopted for MacOS

Render deformable 3D Gaussian Splats using Metal on Apple platforms

Minimal Claude Code alternative powered by MLX

Code for the paper: "Modular Neural Image Signal Processing". A modular neural ISP with interpretable stages, multi-style rendering, cross-camera generalization, and post-editable re-rendering with…

Render Gaussian Splats using Metal on Apple platforms (iOS/iPhone/iPad, macOS, and visionOS)

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

ArtNet Swift library

A 3D Graphics Framework built on Apple's Metal

Examples using MLX Swift

Try CoreML models on multiple images and videos easily and quickly

SwiftUI for terminal applications

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

JavaScript implementation of Philip J. Schneider's "Algorithm for Automatically Fitting Digitized Curves" from the book "Graphics Gems". Converted from Python implementation.

A swift extension on NSTokenField which makes it highly customizable and removes a lot of boilerplate code from implementation

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

Software defined VHS decoder - Fork (maybe temporary) of the ld-decode Laserdisc rf decoder

openvino version of openai/whisper

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.

The friendly PIL fork

Python Module for SMPTE Time Code Manipulation

CPU/GPU Implementation of the SCAMP algorithm for computing the matrix profile

A subclass of NSTokenField that allows token customization.

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

Imagewang self supervised experiments

Convolutional Neural Networks to predict the aesthetic and technical quality of images.

StyleGAN Encoder - converts real images to latent space

Numpy for swift through Accelerate

A simple browser that shares the window using a Syphon server

• scheib's chromium fork. • 2017 and earlier, this served as the GitHub chromium mirror. In 2018 the mirror was moved to https://github.com/chromium/chromium as an official mirror updated by chromi…