JSPM

AI SDK by Vercel - The AI Toolkit for TypeScript and JavaScript

Core LangChain.js abstractions and schemas

OpenAI integrations for LangChain.js

Typescript bindings for langchain

Promptbook: Run AI apps in plain human language across multiple models and platforms

Superfast runtime validators with only one line

Anthropic integrations for LangChain.js

OpenAPI definitions and converters for 'typia' and 'nestia'.

Mastra is the Typescript framework for building AI agents and assistants. It’s used by some of the largest companies in the world to build internal AI automation tooling and customer-facing agents.

The AI SDK for building declarative and composable AI-powered LLM products.

cli for mastra

<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>

environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker

Official JavaScript library for Tavily.

Fast and lightweight token estimation for any LLM without requiring a full tokenizer

PostHog Node.js AI integrations

A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.

Hardware accelerated language model chats on browsers

OpenInference Core provides utilities shared by all OpenInference SDK packages.

A tool to pack repository contents to single file for AI consumption

The Memory Layer For Your AI Apps

GitHub Action for evaluating MCP server tool calls using LLM-based scoring

Community AI SDK provider for Google Gemini using the official CLI/SDK

Use Claude Code without an Anthropics account and route it to another LLM provider

The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.

| [NPM Package](https://www.npmjs.com/package/@mlc-ai/web-tokenizers) | [WebLLM](https://github.com/mlc-ai/web-llm) |

structured outputs for llms

MCP server for Gemini CLI integration

OpenTelemetry instrumentation for the `openai` OpenAI client library

A client for node or the browser to generate and consume streaming json

OpenInference utilities for ingesting Vercel AI SDK spans

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

A powerful TypeScript library for building AI agents with multi-threaded conversations, tool execution, and event handling capabilities

Agentic AI utils which work with any LLM and TypeScript AI SDK.

JavaScript and TypeScript client for Gradient AI

A client for the Phoenix API

nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

DOM to Semantic-Markdown for use in LLMs

Themes and CSS files for nlux, the JavaScript and React library for building conversational AI interfaces.

Generate Markdown versions of Docusaurus HTML pages and an llms.txt index file

JS tokenizer for LLaMA-based LLMs

ocr documents using gpt-4o-mini

AniList MCP server for accessing AniList API data

ClinicalTrials.gov Model Context Protocol (MCP) Server that provides a suite of tools for interacting with the official ClinicalTrials.gov v2 API. Enables AI agents and LLMs to programmatically search, retrieve, and analyze clinical trial data.

The TypeScript library for building AI applications.

A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow

Promptbook: Run AI apps in plain human language across multiple models and platforms

Core library using Vercel AI SDK for OpenAssistant

Universal AI Development Platform with working MCP integration, multi-provider support, and professional CLI. Built-in tools operational, 58+ external MCP servers discoverable. Connect to filesystem, GitHub, database operations, and more. Build, test, and

ping AI provider to check if a api key is valid

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

JS tokenizer for LLaMA 3

Websocket client to connect to your chainlit app.

Build conversational bots that can do anything with the help of ChatGPT and other LLM's.

A "Notion-style" block-based extensible text editor built on top of Prosemirror and Tiptap.

Create Mastra apps with one command

LLM Gateway - Regex Hidder Plugin

AI Agent Kit for 1inch - Connect any LLM to 1inch DeFi protocols

A CLI for GenAIScript, a generative AI scripting framework.

Node.js wrapper for the probe code search tool

VitePress plugin to generate llms.txt files automatically

Promptbook: Run AI apps in plain human language across multiple models and platforms

Advanced n8n Notion nodes: Full-featured workflow node + AI Agent Tool for intelligent Notion automation with 25+ block types (BETA)

- Convert a **stream of token** into a **parsable JSON** object before the stream ends. - Implement **Streaming UI** in **LLM**-based AI application. - Leverage **OpenAI Function Calling** for early stream processing. - Parse **JSON stream** into distinct

Light weight JSON Schema $ref resolver. Expands a JSON Schema by resolving `$ref` references from a mapping of definitions. Does not handle remote references. Has comprehensive unit tests and no dependencies.

LLM Gateway Core - Main proxy server

SDK for LLM Gateway plugin development

Promptbook: Run AI apps in plain human language across multiple models and platforms

🧠 AI Memory System powered by MongoDB Atlas & Voyage AI - Autonomous memory management with zero manual work

Meld: A template language for LLM prompts

Fully typed chat APIs for OpenAI and Azure's chat models - with token checking and retries

OpenAI LLM function schema from OpenAPI (Swagger) document

Promptbook: Run AI apps in plain human language across multiple models and platforms

The LangServe adapters for nlux React, the React JS library for building conversational AI interfaces.

The LangChain adapters for nlux, the javascript library for building conversational AI interfaces.

n8n node to interact with the Perplexity AI API

Syntax highlighter for nlux

Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MC

Server-Sent Events (SSE) support for Fetcher HTTP client with native LLM streaming API support. Enables real-time data streaming and token-by-token LLM response handling.

MCP server for Sequential Thinking Tools

A simple MCP server that provides timestamp-based UUIDs

A TypeScript library for extracting structured and grounded information from text using LLMs

Interfaces for extending the embedjs ecosystem

Get structured, fully typed JSON outputs from OpenAI and Anthropic LLMs

A Javascript Client SDK for the Linkup API

Node.js/TypeScript MCP server for Atlassian Jira. Equips AI systems (LLMs) with tools to list/get projects, search/get issues (using JQL/ID), and view dev info (commits, PRs). Connects AI capabilities directly into Jira project management and issue tracki

Create plain Markdown from OpenAPI documents (for LLMs)

Customized MCP Server for Shopify API (by Infiria)

Promptbook: Run AI apps in plain human language across multiple models and platforms

Ultra-lightweight (2.7kB min+gzip) HTTP client with built-in path parameters, query parameters, and Axios-like API. The foundation of the Fetcher ecosystem with powerful interceptor system and LLM streaming API support.

Superfast runtime validators with only one line

> AI-powered CLI tool for commit messages **and** pull request reviews — using local models.

LaunchDarkly AI SDK for Server-Side JavaScript

Pure JavaScript minimal lossless JSON parse event streaming, akin to SAX. Fast, modular, and dependency-free.

Promptbook: Run AI apps in plain human language across multiple models and platforms

Useful util functions when extending the embedjs ecosystem

OpenAI Fastify plugin

MCP server that enables AI agents to perform intelligent web searches using OpenAI's o3 model with natural language queries

A Model Context Protocol server that acts as an intelligent conversation state manager and development guide for LLMs, featuring comprehensive long-term memory with persistent project artifacts

WorkflowAI JS SDK

The Web AI Framework's core - BaseAI.dev

Promptbook: Run AI apps in plain human language across multiple models and platforms

TS tokenizer for Mistral-based LLMs

Open-source CLI that initializes ./.qlood in your project and uses AI-driven browser automation to test your web app.

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Prompt Orchestration Markup Language

An MCP server that provides read-only access to MySQL databases.

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Convert strings to mathematical videos using Groq API and Manim

Promptbook: Run AI apps in plain human language across multiple models and platforms

Google Maps MCP server with streamable HTTP transport support for location services, geocoding, and navigation

Promptbook: Run AI apps in plain human language across multiple models and platforms

Web page loader for embedjs

XML loader for embedjs

| [NPM Package](https://www.npmjs.com/package/@mlc-ai/web-tokenizers) | [WebLLM](https://github.com/mlc-ai/web-llm) |

An MCP server that provides access to n8n workflows, executions, credentials, and more through the Model Context Protocol

PDF loader for embedjs

MCP server for integrating Omnisearch with LLMs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Simple MCP server for Claude Code one-shot execution

Official API wrapper for DeepInfra

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Google Calendar MCP Server with extensive support for calendar management

Promptbook: Run AI apps in plain human language across multiple models and platforms

Promptbook: Run AI apps in plain human language across multiple models and platforms

Production-ready PubMed Model Context Protocol (MCP) server that empowers AI agents and research tools with comprehensive access to PubMed's article database. Enables advanced, automated LLM workflows for searching, retrieving, analyzing, and visualizing

Structure-focused web scraper optimized for LLMs for use with MCP with minimal console output. Configure output directory with PRYSM_OUTPUT_DIR environment variable.

Promptbook: Run AI apps in plain human language across multiple models and platforms

An MCP server implementing the think tool for Claude and other LLMs

Promptbook: Run AI apps in plain human language across multiple models and platforms

Add LibSQL support to embedjs

RAG search system for Gist, GitHub, and Local Files.

Word, PPT and Excel loader for embedjs

Sitemap recursive loader for embedjs

Load images into embedjs

CSV loader for embedjs

MCP server for Perplexity search

OpenTelemetry instrumentation for the `openai` OpenAI client library

A Model Context Protocol (MCP) server implementation that provides real-time web search capabilities through a simple API

Promptbook: Run AI apps in plain human language across multiple models and platforms

Voyp Model Context Protocol server

XML loader for embedjs

MCP server for interacting with LLMs using LlamaIndexTS

Typescript SDK for AskNews API

HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models with OpenAPI/Swagger integration

MCP server to migrate data out of code (ts/js) into config (json)

A declarative engine for building native desktop applications with web technologies, designed for LLM architects.

A Model Context Protocol (MCP) implementation for workflow management and automation.

Model Context Protocol server for Base network blockchain operations

Skynet Agent Framework - Create and manage AI agents with flows and plugins

Promptbook: Run AI apps in plain human language across multiple models and platforms

Simplify building LLM-powered apps with easy-to-use base components, supporting text and chat-based prompts with handlebars template engine, output parsers, and flexible function calling capabilities.

Promptbook: Run AI apps in plain human language across multiple models and platforms

MCP server for JinaAI reader

Promptbook: Run AI apps in plain human language across multiple models and platforms

MCP server for integrating Tavily search API with LLMs, providing web search, RAG context generation, and QnA capabilities

A beginner-friendly guide server that helps users understand MCP concepts, provides interactive examples, and demonstrates best practices for building MCP integrations.

Standard library of AI functions which work with any LLM and TypeScript AI SDK.

eval-genius enables evals of arbitrary async code. It is generally intended for making multiple assertions on outputs which are generated nondeterministically. These assertions can be used to score algorithms on their effectiveness.

A Model Context Protocol server for web search using DuckDuckGo and Felo AI

Simple and easy agent framework, include various of structured data manipulation, agent and function compositing, code editing, fs and more!

MCP server for Android Debug Bridge (ADB) interactions in TypeScript

Model Context Protocol server for Sonic Pi

Promptbook: Run AI apps in plain human language across multiple models and platforms

A NodeJS RAG framework to easily work with LLMs and custom datasets

Promptbook: Run AI apps in plain human language across multiple models and platforms

Enable usage of OpenAI models with embedjs

One interface to hundreds of LLM models, zero dependencies, tons of features, for Browser and Node.js

MCP server for consulting powerful AI models

A Model Context Protocol server for nostrdb enabling LLMs to query nostr via the nostrdb command line tool.

🚀 **Transform feature requests into production-ready code in seconds**

A model context protocol server for Jira API.

High-performance CCXT MCP server for cryptocurrency exchange integration

Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP in

An MCP server that provides LLMs with the ability to use GitHub issues as tasks

MCP Document Converter Server — A Model Context Protocol server for seamless document format conversion and processing

Markdown Content Preprocessor - Fetch web pages, extract content, convert to clean Markdown

LLM provider abstraction layer with unified streaming interface

MCP server implementation for MySQL database access

A Model Context Protocol server for managing GitHub issues as Kanban using gh CLI

A Model Context Protocol (MCP) server that exposes the official Notion SDK

Generates MCP server code from OpenAPI specifications

Ready-to-use tools for Grid LLM orchestration

Open-source AI agent framework for building autonomous systems that solve real-world tasks effectively.

GitLab MCP Server - A Model Context Protocol server for GitLab integration

Shared utilities for Octocode MCP packages

Solar LLM and Embeddings nodes for n8n

MCP Server for interacting with the IPFS Storacha Network

Promptbook: Run AI apps in plain human language across multiple models and platforms

Enable usage of Ollama with embedjs

A Model Context Protocol (MCP) server for Tana

Scrape and extract structured data from a webpage using ScrapeGraphAI's APIs.

MCP server for JinaAI search

An easy way to run AI models in React Native with ExecuTorch

A Model Context Protocol server for analyzing text documents with word and character counting capabilities

🍪 A gamified MCP server that rewards LLMs with cookies for quality responses through honest self-reflection

Shell command execution MCP server

MCP server for integrating Turso with LLMs

a mcp server to get sentry issue by id or url for LLM

An MCP server that bridges the gap between your applications and various LLM providers

Run AI prediction functions in Unity Engine.

Model Context Protocol (MCP) server for the Salesforce CLI, making Salesforce CLI commands available to LLM tools like Claude Desktop.

MCP server for interacting with Manifold Markets prediction markets

Model Context Protocol (MCP) server for seamless integration with Onyx AI knowledge bases

JavaScript library to repair broken/invalid JSON strings, especially from LLM outputs

AI-Native Logging for LLM Agent Development - TypeScript/Node.js Implementation

AI-Assisted Software Engineering (AASWE) - Rich codebase context for IDE LLMs

A Model Context Protocol (MCP) server that acts as a passthrough proxy with hook middleware support

Generate beautiful HTML adventure websites from your codebase

The OpenAI adapters for nlux, the javascript library for building conversational AI interfaces.

⚡ Wire up your AI prompts - The ultimate CLI for AI workflow orchestration. Create, manage, and chain prompts across 400+ AI platforms with enterprise security, version control, and automation. Includes comprehensive CLI documentation.

Model Context Protocol (MCP) server for eRegulations API

MCP server for JinaAI grounding

MCP Server for managing LLM prompts

Smart file filter for Repomix - search and bundle only files containing specific strings

MCP Server for executing shell commands from MCP clients, particularly useful for Xcode-related operations

The OpenAI adapters for nlux React, the React JS library for building conversational AI interfaces.

The Scrypted LLM plugin allows connecting to various LLM providers, or running your own locally.

JS tokenizer for Mistral-based LLMs

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

A Model Context Protocol server for MongoDB connections

MCP server for extracting and converting images to base64 for LLM analysis

Core primitives for LLM orchestration and agentic workflows

copilot-js is a library that provides an autocompletion for LLM.

Create browser automations with an LLM agent and replay them as Playwright scripts.

Route Recoder CLI requests to different LLM providers including Kimi K2, Qwen 3, and DeepSeek R1

A Model Context Protocol server for Vitest test execution and management

Use MDX to render high quality LLM prompts

Reusable UI components and renderer for Monza.ai extension and applications.

Prebuilt UI components for LLMAsAService.io

Custom jest matchers for testing AI applications

Official SDK for Magically - Build mobile apps with AI

A powerful AI agent toolkit compatible with @openai/agents for building conversational AI with tool calling support using OpenRouter

Vercel AI SDK Provider for Ollama using official ollama-js library

llama.cpp gguf file parser for javascript

Intelligent CLI tool with AI-powered model selection that analyzes your hardware and recommends optimal LLM models for your system

MCP server for semantic prompt framework - NLP-inspired adaptive reasoning engine for LLM orchestration

LLM coder 'tools' for any model

Model Context Protocol (MCP) server for Okta API operations with support for bulk operations and caching

A light and modern interface for Helicone's generateRouter API

Node.js Library for Large Language Model LLaMA/RWKV

A client for interacting with AWS Bedrock and MCP servers

Docusaurus plugin that adds a copy page button to extract documentation content as markdown for AI tools like ChatGPT and Claude

A Reactive CLI that generates commit messages for Git and Jujutsu with various AI

Promptbook: Run AI apps in plain human language across multiple models and platforms