Backend-agnostic spec-template registry: git/huggingface/npm/local backends + TTL cache + sigstore-style signature verification (Section 40)

llama.cpp CLI tool - pure Node.js, no Python required. Download & run GGUF models from HuggingFace, ModelScope, or Ollama Registry. One-command setup for llama.cpp binaries.

Pure Node.js MCP server for downloading HuggingFace models with enhanced HTTP API and smart filtering

Use the Space mini_header outside Hugging Face

Enable usage of HuggingFace models with embedjs

MCP server for huggingface integration

Semantic Kernel Typescript - HuggingFace

TraceAI instrumentation for HuggingFace Inference API

js bindings for huggingface tokenizers

Chatbot maker for HuggingFace Inference API and other AI API providers and backends.

Hugging Face provider package for OffRouter.

Various utilities for maintaining Ollama compatibility with models on Hugging Face hub

CODOZ - Real Data Engine. Fetch real-world ML datasets from Kaggle, UCI, HuggingFace

simple huggingface inference module

Hugging Face Spaces 搜索 — 纯 http recipe（明文 JSON，huggingface.co/api/spaces，无签名）。 迁自本地 RSSHub 路由 lib/routes/huggingface/spaces.ts。响应是根级数组 SpaceItem[]，用 itemsAt:"" 取根（引擎空路径=identity）。只保留默认过滤（sdk/hardware/running=all，无需引擎侧过滤），search 由 接口完成。

Hugging Face inference integration package for Playrunner.

Private/offline browser-side document chunking and embedding for Knowledge Base using bundled ONNX models via @huggingface/transformers.

Local embedder and reranker for Eidentic — run bge-small-en-v1.5 and cross-encoder reranking via @huggingface/transformers, no API key required.

Hugging Face OAuth and provider-specific model routes for Pi

Download models from CivitAI and upload them to HuggingFace Hub as proper model repos