Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more. JSON-first, no interactive prompts

vibe coded eval

A framework for efficient model inference with omni-modality models

MLX-Video is the best package for inference and finetuning of Image-Video-Audio generation models on your Mac using MLX.

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment

Inworld TTS

Unsloth Studio is a web UI for training and running open models like Qwen3.5, Gemma 4, DeepSeek, gpt-oss locally.

Whisper realtime streaming for long speech-to-text transcription and translation

A simple MLX implementation for pretraining LLMs on Apple Silicon.

[NIPS2025] VideoChat-R1 & R1.5: Enhancing Spatio-Temporal Perception and Reasoning via Reinforcement Fine-Tuning

[ACL-2026] MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search tools.

Modern C++ Programming Course (C++03/11/14/17/20/23/26)

Open-source AI cookbook

A fork to add multimodal model training to open-r1

Model Activity Visualiser

Run LLMs with MLX

MLX binary vectors and associated algorithms.

Googles NotebookLM but local

gsm8k eval in MLX.

Minimal reproduction of DeepSeek R1-Zero

Python examples for securing an API and invoking it as a service user

A cheatsheet of modern C++ language and library features.

This repository is a curated collection of resources, tutorials, and practical examples designed to guide you through the journey of mastering CUDA programming. Whether you're just starting or look…

LLM KV cache compression made easy

This is the React sample used in the ZITADEL quick start guide.

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models