ML Claw: deploy OpenClaw agents on Hugging Face

A Python port of Pi’s minimalist coding agent.

A high-performance, in-memory virtual file system for Markdown files. Unix-like commands, Git-style versioning, content-addressable storage, and multi-user permissions — built in Rust.

Archived — ML Intern is no longer maintained. Continue with HuggingChat.

Agents in llama.cpp

A minimal LLM-powered zero-day vulnerability scanner by AISLE.

Backup, publish, and install OpenClaw agents on the Hugging Face Hub

AI agents running research on Hugging Face infra

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

HF CLI extension to run local coding agent powered by llmfit and llama.cpp

OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.

Give your agents the power of the Hugging Face ecosystem

An interface library for RL post training with environments.

Reachy Mini's SDK

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

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

Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe

A library for working with prompt templates locally or on the Hugging Face Hub.

A Lightweight Library for AI Observability

Training and inference on AWS Trainium and Inferentia chips.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

Build voice agents with open-source models

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

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

Minimalistic large language model 3D-parallelism training

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.