The AI coding agent built for the terminal.

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Making the community's best AI chat models available to everyone.

A framework to easily use 37 (and growing) different image matching methods

A package that provides semantically versioned access to llama.cpp in your Swift projects.

TPU inference for vLLM, with unified JAX and PyTorch support.

A Swift client for Hugging Face Hub and Inference Providers APIs

WIP

An API-compatible, drop-in replacement for Apple's Foundation Models framework with support for custom language model providers.

🖥 Windows Bootable USB creator for macOS. 🛠 Patches Windows 11 to bypass TPM and Secure Boot requirements. 👾 UEFI & Legacy Support

A collection of guides and examples for the Gemma open models from Google.

MTEB: Massive Text Embedding Benchmark

Fast, Flexible and Portable Structured Generation

[DEIMv2] Real Time Object Detection Meets DINOv3

precision colorscheme for the vim text editor

A curated list of awesome commands, files, and workflows for Claude Code

MCP generator for OpenAPIs 🫳🎤💥

Get your documents ready for gen AI

Intelligent Router for Mixture-of-Models

Artificial Neural Engine Machine Learning Library

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

Torch feature parity for MLX

Notebooks using the Hugging Face libraries 🤗

Native Apple Silicon LLM server on MLX with chat UI, menu bar app, and CLI. OpenAI & Ollama compatible. Supports Apple Foundation Models.

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]