Hugging Face

Storage Buckets v1.0

Storage Buckets is a feature introduced by Hugging Face to provide mutable, S3-like object storage on the Hugging Face Hub. Designed for machine learning workflows, it allows users to store models, datasets, and artifacts without the overhead of version control. Built on the Xet storage backend, it offers efficient deduplication and fast data transfers.

Daggr vBeta

Daggr is an open-source Python library designed to streamline the creation of AI workflows by connecting Gradio apps, machine learning models, and custom functions. It automatically generates a visual canvas for inspecting intermediate outputs, rerunning individual steps, and managing state within complex pipelines, all through concise Python code.

physics-intern vinitial release

An autonomous agentic framework for physics research built by David Louapre (Hugging Face AI Scientist). Accepts theoretical physics questions in plain text, automatically breaks problems into steps, assigns specialized sub-agents, and reasons through solutions step by step.

Hugging Face Skills v0.1.0

Hugging Face Skills are Agent Context Protocol (ACP) definitions for AI/ML tasks like dataset creation, model training, and evaluation. They are interoperable with all major coding agent tools like OpenAI Codex, Anthropic's Claude Code, Google DeepMind's Gemini CLI, and Cursor.