Official data.gouv.fr Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the French national Open Data platform, directly through conversation.

🛥 Vaporetto: Very accelerated pointwise prediction based tokenizer

Fast Tokens

Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.

A collection of advanced CSS styles to create realistic-looking effects for the faces of Pokemon cards.

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

xet client tech, used in huggingface_hub

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

A Small C Compiler

egui: an easy-to-use immediate mode GUI in Rust that runs on both web and native

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

🤗 Tokenizers.js: A pure JS/TS implementation of today's most used tokenizers

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Linux kernel source tree

Build smaller, faster, and more secure desktop and mobile applications with a web frontend.

Datamodels for hugging face tokenizers

🔀 yet another mixture of experts

The simplest way to serve AI/ML models in production

Anki is a smart spaced repetition flashcard program

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Agentic RL Training at Scale

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

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

🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

ONNX runtime for Flutter.

👷 Build compute kernels

Fast and memory-efficient exact attention