State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Result-integration boundary over @huggingface/transformers for browser consumers (loadPipeline, classify, classifyAll, embed)
Result-integration boundary over @huggingface/transformers for Node consumers (loadPipeline, classify, classifyAll, embed)
A langchain adapter for Huggingface transformers
Local-models BaseProvider backed by @huggingface/transformers and kokoro-js (chat, TTS, ASR, embeddings)
Private/offline browser-side document chunking and embedding for Knowledge Base using bundled ONNX models via @huggingface/transformers.
Use @huggingface/transformers in Expo and React Native apps through onnxruntime-react-native.
HuggingFace Transformers.js provider for @workglow/ai.
On-device embeddings for @mnemehq/sdk via @huggingface/transformers. Zero-config local mode with Xenova/all-MiniLM-L6-v2.
Local-model text embeddings for self-hosted ggui. Provides a cold-start lifecycle (model download, cache resolution, warmup events) and a `@huggingface/transformers`-backed embedding provider running entirely on-device — no embedding API key required.
On-device LLM engine. Wraps @huggingface/transformers + ONNX Runtime Web behind a narrow Engine surface. Presets ship Gemma 4 (E2B/E4B) configurations. Adapters in subpaths satisfy @inbrowser/relay's InferenceProvider and @inbrowser/agent's LlmClient so a
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Run Hugging Face onnx-community models locally inside pi: registers a chat provider for ONNX text-generation models and a set of tools (embeddings, classification, ASR) backed by @huggingface/transformers and onnxruntime-node.
A ready-to-use vector database/RAG TypeScript library implemented with SQLite and @huggingface/transformers.
Open-source text-to-video and image-to-video generation library using CogVideoX model, inspired by @huggingface/transformers
Collective of common transformers transformers for Shiki
Chroma's fork of @xenova/transformers serving as our default embedding function
Transformers.js wrapper makes it easy to use with xsai
NodeJS implementation of @Qdrant/fastembed
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Reusable transformers for patching RPC inputs and outputs
🤗 Tokenizers.js: A pure JS/TS implementation of today's most used tokenizers
Automatic KV-Cache Optimization for HuggingFace Transformers - Find the optimal cache strategy, attention backend, and configuration for your model and hardware.
Typescript client for the Hugging Face Inference Providers and Inference Endpoints
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.