vb

pretext. Fast, accurate & comprehensive text measurement & layout

symphony. Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

oai-skills. The contents of /home/oai/skills in ChatGPT's code interpreter environment

circuit_sparsity. Open-source release accompanying Gao et al. 2025

qmd. mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

parakeet.js. NVIDIA Parakeet speech recognition for the browser (WebGPU/WASM) powered by ONNX Runtime Web

skills. Give your agents the power of the Hugging Face ecosystem

VLAb. Python

dllm. dLLM: Simple Diffusion Language Modeling

cmd-k. cmd-k converts written instruction into executable shell commands, cursor command k that works from the terminal.

reachy_mini. Reachy Mini's SDK

try. fresh directories for every vibe

reachy_mini_conversation_app. Talk with Reachy Mini!

chat-ui-swift. A SwiftUI chat application showcasing AnyLanguageModel and swift-huggingface

stagehand. The SDK For Browser Agents

TextArena. A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

DeepSeek-OCR. Contexts Optical Compression

helion. A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.

reflex. 🕸️ Web apps in pure Python 🐍

Llama-macOS. A cosy home for your LLMs.

openai-sora-sample-app. Sample app to get started using the Video API with Sora

OpenEnv. An interface library for RL post training with environments.

gpt2-from-scratch-from-scratch. Rust

nanochat. The best ChatGPT that $100 can buy.

Karabiner-Elements. Karabiner-Elements is a powerful tool for customizing keyboards on macOS

openai-apps-sdk-examples. Example apps for the Apps SDK

F3. [SIGMOD 2026] F3: The Open-Source Data File Format for the Future

OpenAI. Swift community driven package for OpenAI public API

mcp-jupyter. Python

tinker. Training API and CLI

tinker-cookbook. Post-training with Tinker

inference-providers-starter-app. TypeScript

kalosm. Instant, controllable, local pre-trained AI models in Rust

swift-jinja. A minimalistic Swift implementation of the Jinja templating engine, specifically designed for parsing and rendering ML chat templates.

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

huggingface-vscode-chat. A VSCode extension to use Hugging Face Inference Providers in Copilot Chat

trending-deploy. Python

mlx-genkit. Torch feature parity for MLX

index-tts. An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

checkpoint-engine. Checkpoint-engine is a simple middleware to update model weights in LLM inference engines

batch_invariant_ops. Python

osaurus. Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

trl-jobs. Train LLM on Hugging Face infra

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

marvis-tts. Python

KittenTTS. State-of-the-art TTS model under 25MB 😻

VibeVoice. Open-Source Frontier Voice AI

VyvoTTS. VyvoTTS: LLM-Based Text-to-Speech Training Framework

agents.md. AGENTS.md — a simple, open format for guiding coding agents

goose. an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

cookbook. Open-source AI cookbook

mcp-with-openai-gpt-oss.

fast-agent. Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

aisheets. Build, enrich, and transform datasets using AI models with no code

harmony. Renderer for the harmony response format to be used with gpt-oss

gpt-oss-recipes. Collection of scripts and notebooks for OpenAI's latest GPT OSS models

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

float4. MXFP4-compatible 4-bit floating point types and block formats for Rust.

tts. Inworld TTS

higgs-audio. Text-audio foundation model from Boson AI

BRIA-3.2. GitHub repository for the Bria 3.2 pipeline

cline. Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

infinite-kanvas. An infinite canvas image editor using fal.ai

Context. Native macOS client for Model Context Protocol (MCP)

ttstune. WIP • Untested • Not ready yet

hibiki. Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.

ThinkSound. [NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.

cherry-studio. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

responses.js. A lightweight express.js server implementing OpenAI’s Responses API, built on top of Chat Completions, powered by Hugging Face Inference Providers.

vscode-copilot-chat. Copilot Chat extension for VS Code

bestline-swift. Swift wrapper for @jart's bestline, an ANSI Standard X3.64 teletypewriter command session library

openai-cookbook. Examples and guides for using the OpenAI API

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

simpletransformers. Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

open-responses-server. Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

videoprism. Official repository for "VideoPrism: A Foundational Visual Encoder for Video Understanding" (ICML 2024)

BlaGPT. Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.

nano-vllm. Nano vLLM

delayed-streams-modeling. Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

iMCP. A macOS app that provides an MCP server to your Messages, Contacts, Reminders and more

top-cvpr-2025-papers. About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

cocogold. Marigold-based CoCo Segmentation

cosmopolitan. build-once run-anywhere c library

trackio. A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗

mlx-lm. Run LLMs with MLX

MonkeyOCR. A lightweight LMM-based Document Parsing Model

shit.

UniWorld. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

safetensors_explorer. CLI utility to inspect and explore .safetensors and .gguf files

llama-swap. Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

diffuseR. an R port of huggingface/diffusers

container. A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.

monarch. PyTorch Single Controller

WSL. Windows Subsystem for Linux

PlayDiffusion. Python

gallery. A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

TermOS. An operating system in your terminal

pyscript. An open source platform for Python in the browser. https://pyscript.net Docs: https://docs.pyscript.net/ Try it: https://pyscript.com/ Community: https://discord.gg/HxvBtukrg2

chatterbox. SoTA open-source TTS

cactus. Low-latency AI engine for mobile devices & wearables

Megakernels. Kernels, of the mega variety :)

rust-sdk. The official Rust SDK for the Model Context Protocol

tt-tiny. tiny code to access tenstorrent blackhole

LLaSA_Plus. Llasa Speed Up

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

whispering. Rust

paddler. Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

fastrtc. The python library for real-time communication

MMaDA. MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

AgentCPM-GUI. AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

ten-vad. Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

codex. Lightweight coding agent that runs in your terminal

grok-prompts. Prompts for our Grok chat assistant and the `@grok` bot on X.

mcp-course. MDX

smolvlm-realtime-webcam. Real-time webcam demo with SmolVLM and llama.cpp server

ty. An extremely fast Python type checker and language server, written in Rust.

hfendpoints. SDK for creating Hugging Face Inference Endpoints deployments

nanoVLM. The simplest, fastest repository for training/finetuning small-sized VLMs.

sps. Rust based package manager for macOS

ring-flash-attention. Ring attention implementation with flash attention

BitNet. Official inference framework for 1-bit LLMs

gsplat.js. JavaScript Gaussian Splatting library.

OpenBench. Open-source reproducible benchmarks from Argmax

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

universal-intelligence. ◉ Universal Intelligence: AI made simple.

ttach. Image Test Time Augmentation with PyTorch!

hfjobs-menubar. OSX hfjobs menubar app

hfjobs. Hugging Face Jobs

ggml-easy. Thin wrapper around GGML to make life easier

MegaTTS3. Python

LTX-Video-Trainer. Community trainer for Lightricks' LTX Video model 🎬 ⚡️

Orpheus-TTS. Towards Human-Sounding Speech

mlx-audio. 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.

gemma. Gemma open-weight LLM library, from Google DeepMind

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

realtime-transcription-fastrtc. Real Time Speech Transcription with FastRTC ⚡️and Local Whisper 🤗

VoiceInk. The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription

Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

mcp-hfspace. MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.

csm. A Conversational Speech Generation Model

smartfunc. Turn docstrings into LLM-functions

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

NeoBERT. Python

acu. A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

HuggingSnap. SmolVLM2 Demo

LiteASR. [EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

onnx-safetensors. Use safetensors with ONNX 🤗

OpenF5-TTS. (WIP) A retrain of F5-TTS on permissively-licensed data

olmocr. Toolkit for linearizing PDFs for LLM datasets/training

kaudio. Rust crate for some audio utilities

chat-ui. The open source codebase powering HuggingChat

computer-vision-course. This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

rocm-nix. ROCm overlay for TGI and kernel-builder

blog. Public repo for HF blog posts

tgi-gaudi. Large Language Model Text Generation Inference on Habana Gaudi

optimum-habana. Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)

Spark-TTS. Spark-TTS Inference Code

gpu-fryer. Where GPUs get cooked 👩‍🍳🔥

LLaDA. Official PyTorch implementation for "Large Language Diffusion Models"

DeepEP. DeepEP: an efficient expert-parallel communication library

kernels. Build compute kernels and load them from the Hub.

Learning-Audio-ML.

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

just. 🤖 Just a command runner

swift-tokenizers. Wrapping C `tokenizers` in ergonomic, safe Swift.

Zonos. Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

OLMoE.swift. Swift

agents-course. This repository contains the Hugging Face Agents Course.

sec. Tiny library for using secrets in Python applications

mergekit-LGPL. Tools for merging pretrained large language models.

bpe.zig. Minimal implementation of a Byte Pair Encoding (BPE) tokenizer in Zig

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

litert-torch. Support PyTorch model conversion with LiteRT.

ramalama. RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.

Math-Verify. Python

rlhf-book. Textbook on reinforcement learning from human feedback

tt-buda. Tenstorrent TT-BUDA Repository

kokoro. https://hf.co/hexgrad/Kokoro-82M

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

swift-hub. Swift

DeepSeek-R1.

DeepSeek-LLM. DeepSeek LLM: Let there be answers

TinyZero. Minimal reproduction of DeepSeek R1-Zero

open-r1. Fully open reproduction of DeepSeek-R1

X-Codec-2.0. Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

mcp-openai-gemini-llama-example. Python

ort. Fast ML inference & training for ONNX models in Rust

simpletts. A lightweight Python library for running TTS models with a unified API.

zig. Moved to Codeberg

kokorojs. kokoro text to speech using javascript

micro_diffusion. Official repository for our work on micro-budget training of large-scale diffusion models.

LuminaBrush. Illumination Drawing Tools for Text-to-Image Diffusion Models

moondream. tiny vision language model

InstantCoder. Create apps with Gemini

WindowsAgentArena. Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

bat. A cat(1) clone with wings.

OmniParser. A simple screen parsing tool towards pure vision based GUI agent