JSPM

The Hermes runtime, used by React Native for Android, is able to output [Chrome Trace Events](https://docs.google.com/document/d/1CvAClvFfyA5R-PhYUmn5OOQtYMH4h6I0nSsKchNAySU/preview) in JSON Object Format.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

<h1 align="center"> Hermes Profile Transformer </h1>

Wraps templates with layouts. Layouts can use other layouts and be nested to any depth. This can be used 100% standalone to wrap any kind of file with banners, headers or footer content. Use for markdown, HTML, handlebars views, lo-dash templates, etc. La

Primus is a simple abstraction around real-time frameworks. It allows you to easily switch between different frameworks without any code changes.

Chroma's fork of @xenova/transformers serving as our default embedding function

a lightweight no-dependency fork of transformers.js (only tokenizers)

<!-- README for NPM; the one for GitHub is in .github directory. -->

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

A highly reduced fork of the Xenova JavaScript port of 🤗 transformers. Node.js only, with a lot of functionality removed.

Serialize rich data-types with support for defining relationships with other transformers

JS SDK for running quantized small language models in the browser

Mean Transformers

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Production-ready MCP server for document ingestion and knowledge management with vector search. Supports PDF, DOCX, TXT, MD, CSV, JSON, HTML with ChromaDB and multiple embedding providers.

Primus is a simple abstraction around real-time frameworks. It allows you to easily switch between different frameworks without any code changes.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Disassemble XML files into smaller, more manageable files and reassemble the XML when needed.

Un Méta-SDK pour interagir avec plusieurs fournisseurs d'IA via une interface unifiée.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Lightweight CLI tool and library for detecting AI model drift using embeddings and scalar metrics. Tracks semantic, conceptual, and lexical change over time.

Transformers.js provider for Vercel AI SDK - Run 🤗 Transformers directly in the browser with WebGPU support

Un golem de code autonome qui crée, analyse et pense avec une IA locale propulsée par Transformers.js.

JavaScript/TypeScript Implementation of LLMLingua-2

EntityDB is an in-browser vector database wrapping indexedDB and Transformers.js

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

Node.js plugin for speech recognition that works with OpenAI's Whisper models using ONNX.

Revolutionary embedding-based ATS scoring and skill matching system with dynamic skill discovery for job portal applications

A collections of transformers that parse graphql schema definition language, add specific directives to qualifying fields, and return the parsed document

Smart. Simple. Local. AI-powered semantic search in TypeScript using transformer embeddings. No cloud, no API keys — 100% offline.

large model translator

HuggingFace tokenizer support for Chonkie - extends @chonkiejs/core with real tokenization

Node.js binding for huggingface/tokenizers library

A Node.js package to censor PII in a string using a hybrid NER and Regex approach with comprehensive test coverage. SERVER-SIDE ONLY - will not work in browsers or frontend frameworks. For browser support, see pii-paladin-lite.

An advanced, modular SDK Builder for creating universal API clients in browser and Node.js.

Event transformers and more for lilybird

General-purpose TypeScript plugins/transformers

Local text embedding package with bundled models - works offline

React components and hooks for Wandler

Central Nervous System MCP Server for Autonomous Multi-Agent Orchestration with free local embeddings

A simple, fast, incremental Typescript compiler supporting custom transformers.

connectors and mappers for external platforms logCiCa can interact with

Run any AI model in your browser with WebGPU - no server required

Easy, fast and WASM/WebGPU accelerated vector embedding for the web platform. Locally via ONNX/Transformers.js and via API. Compatible with Browsers, Workers, Web Extensions, Node.js & co.

Convenient interface for utilizing various embedding models via API and locally.

A robust and optimized JavaScript library for integrating Google's Teachable Machine models, supporting various image sources and providing efficient classification capabilities.

Easily use transformers.js with react in browser

Testing @xenova's v3 branch

N8N node for generating text embeddings using Transformer.js with direct text input

transformers.js mod for react-native

Easy, fast and WASM/WebGPU accelerated vector embedding for the web platform. Locally via ONNX/Transformers.js and via API. Compatible with Browsers, Workers, Web Extensions, Node.js & co.

ContextJS - TypeScript compiler with extension support for transformers.

🏠 Teach AI to understand natural language like a patient tutor. Advanced embedding-based function calling with semantic understanding, confidence scoring, and natural language parameter extraction.

A web-first, cross-platform ML framework.

Client for Mighty Inference Server

N8N node for Named Entity Recognition (NER) using Transformer.js

Tiny helper to generate sentence-transformers embeddings via @xenova/transformers in Node.js and the browser.

N8N node for generating image captions using Transformer.js

Convenient interface for utilizing various embedding models via API and locally.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

A lightweight and efficient vector database for storing and searching text embeddings in the browser's local storage. The package supports multiple Embedding providers (OpenAI, Ollama and HuggingFace Transformers) to generate embeddings for text documents

Ultra-lightweight semantic embeddings for event graphs. Browser-first with swappable providers.

Convenient interface for utilizing various ranking models via API and locally.

GPT model implemented with Tensorflow.js

Simple, performant React Hooks for running Transformers.js in your browser.

Library of simple and common data tranformers

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

一个基于原生fetch封装的强大请求库，具备完整的TypeScript支持，满足企业级应用的各种场景

Remix IDE NLUX integration. Remix IDE is the leading IDE for building and deploying smart contracts on Ethereum. NLUX is a JavaScript and React library for building conversational AI experiences.

Add transformers capabilities to Shiki's highlighter

Binds Express and any real time engine through Primus

Modular LLM orchestration framework

Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).

event-based server for jade-lang, minify and transformers

Typescript wrapper for @xenova/transformers

Create Pipe functions, with async and TypeScript support.

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Get random transformers names from 1984 to 2011

Core logic and types for working with transformers

Primus is a simple abstraction around real-time frameworks. It allows you to easily switch between different frameworks without any code changes.

A flexible and lightweight WeChat Official Accounts SDK for Node.js

A flexible and lightweight Paypal SDK for Node.js

Transformer neural networks in the browser

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

A flexible and lightweight Stripe SDK for Node.js

A flexible and lightweight Alipay SDK for Node.js

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

type safe store reducer transformer

Library to add (custom) TypeScript AST transformers to the Angular CLI build pipeline

Get random transformers names

simple huggingface inference module

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

A React provider and hooks for using Hugging Face Transformers.js in React applications with built-in loading states, error handling, and Suspense support

A flexible and lightweight WeChat Mini Program SDK for Node.js

type safe store reducer transformer

Logic for evaluating and executing transformers

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

typescript plus

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

React helpers for using @xenova/transformers

re-ignite is a blazing-fast, modular state management library built for React developers who want powerful control, fine-grained reactivity, and clean architecture without the boilerplate.

strobes component

Vector-based sentence similarity (0.0-1.0) + embedding export. JavaScript implementation inspired by PINTO0309/sentence2simvec

Typescript wrapper for @xenova/transformers

Set of TypeScript transformers that optimize your code before compilation

An auto suggest module which uses context to provide suggestions using NLP

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Universal Re-Rankers Interface

A lightweight and efficient vector database for storing and searching text embeddings in the browser's local storage. The package uses Transformers.js to generate embeddings for text documents and provides functionality for similarity search, filtering, a

An utility to apply custom transformers to @rollup/plugin-typescript

typescript transformer helpers

A speech recognition demo using Hugging Face Transformers

Get random starwars or transformers names

Client-side RAG (Retrieval-Augmented Generation) framework for browsers. Zero server dependency, multi-tier model fallback, production-ready.

A lightweight and efficient vector database for storing and searching text embeddings in the browser's local storage. The package uses OpenAI's API or Transformer.js models to generate embeddings for text documents and provides functionality for similarit

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

AI-powered CLI for customizable image descriptions using Google's Gemini multimodal models.