Hugging Face
The AI community building the future.
Explained projects
speech-to-speech: The Open-Source Voice Agent Built Around Interruption
A modular Python pipeline that swaps in local STT, LLM, and TTS backends, mimics the OpenAI Realtime API, and solves the hardest part of voice UX: stopping cleanly when the user starts talking.
The CPU Strikes Back: Unpacking huggingface/optimum-intel
How a single boolean flag hides a massive C++ compiler, turning standard processors into viable LLM inference engines.
Yet to be explained
pwc-cli
Explain
A Command-Line Interface (CLI), Skill and MCP Server to interact with Papers with Code. For agents and humans.
s2-cli
Explain
A Command-Line Interface (CLI) and Skill to query Semantic Scholar. For agents and humans.
AIFS-single-2.0-on-all-GPUs
Explain
Patch and tutorial to run AIFS single 2.0 using Hugging Face jobs or locally.
physics-intern-claude-plugin
Explain
Claude Code plugin to bootstrap a PhysicsIntern research workspace
pi-local-router
Explain
Pi extension for routing between llama.cpp and Hugging Face Inference Providers
funes-integrations
Explain
funes memory tool integrations for agent harnesses
physics-intern-opencode-plugin
Explain
Installer for Physics Intern inside Opencode
space-demo-kit
Explain
Render polished Gradio-style demo videos for Hugging Face Spaces
physics-intern-codex-plugin
Explain
A Codex plugin for Physics Intern
hf-image
Explain
Fast build, push, pull and run of container images on the Hugging Face registry (cr.hf.co), as an hf CLI extension
wiz-image-action
Explain
GitHub Actions to scan a container image with the Wiz CLI and register its digest with Wiz image trust