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

Lemonade helps users run local LLMs with the highest performance by configuring state-of-the-art inference engines for their NPUs and GPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Tiny Agent: Production-Ready LLM Agent SDK for Every Developer

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

lightweight, python based chat ui

🤗 smolagents: a barebones library for agents that think in code.

A flexible, responsive, and easy-to-use crossword component for React apps.

Virtual environment stacks for Python

Pragmatic approach to parsing import profiles for CI's

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

[WIP] AI Try-On plugin for Chrome

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

Minimalist ML framework for Rust

Tool for exporting GPS files from TomTom Sports Watches

A blazing fast inference solution for text embeddings models

Use Hugging Face with JavaScript

The ultimate Python library in building OAuth, OpenID Connect clients and servers. JWS, JWE, JWK, JWA, JWT included.

LLM powered development for VSCode

🤗 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.

Roadmapper - A Roadmap as Code (Rac) python library. Generate professional roadmap diagram using python code.

Command Line Interface for Hugging Face Inference Endpoints

Open source codebase powering the HuggingChat app

LLM powered development for Neovim

Large Language Model Text Generation Inference

Mirror for resources to local and huggingface

C++ implementation for BLOOM