DeepSeek 4 Flash local inference engine for Metal and CUDA

Harbor is a framework for running agent evaluations and creating and using RL environments.

Speech recognition with word-level timestamps, optimized for batch inference.

Run frontier AI locally.

Our library for RL environments + evals

Apache OpenDAL: One Layer, All Storage.

Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.

Collect, review, and upload redacted pi session files to a Hugging Face dataset

A cosy home for your LLMs.

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Python bindings for llama.cpp

xet client tech, used in huggingface_hub

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

The agent that grows with you

Turn a folder of images into a working IIIF setup – in a minute or less!

An Open Source implementation of Notebook LM with more flexibility and features

A lightweight, lightning-fast, in-process vector database

Open-source library for scalable, reproducible evaluation of AI models and benchmarks.

Per-collection OCR leaderboards using VLM-as-judge

Universal annotation converter

Agent harness to publish your history from Claude Code et al. as Huggingface datasets.

Multilingual Document Layout Parsing in a Single Vision-Language Model

A GitHub Action that syncs your GitHub repository to Hugging Face Hub 🤗

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.

slime is an LLM post-training framework for RL Scaling.

Community maintained hardware plugin for vLLM on Apple Silicon

The Python programming language

Visual Causal Flow