JSPM

SDK for building AI agents with seamless voice-text context switching

Universal MCP server enabling AI clients (Claude Desktop, etc.) to access third-party models (GPT-5, Claude Opus 4, Gemini 2.5 Pro) with intelligent model selection and custom endpoints

Agent-to-Agent Bridge MCP Server with intelligent model fallback, cross-platform support, and automatic installation for Claude Desktop and Claude Code

Native module for An another Node binding of llama.cpp (linux-x64-vulkan)

MCP server wrapper for Google's Gemini CLI

The easiest way to use LLMs, including streams, images, documents, tools and various agent scenarios.

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

Lightweight library for making AI API calls with streaming support

Run AI prediction functions in Unity Engine.

JS tokenizer for Mistral-based LLMs

Native module for An another Node binding of llama.cpp (linux-x64-cuda)

Core primitives for LLM orchestration and agentic workflows

Next generation LLM evaluation framework powered by Vitest.

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

Native module for An another Node binding of llama.cpp (darwin-x64)

Client-side encrypted, audit-ready logging for LLM applications

General-purpose agent with tool calling and session persistence

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

A creative calculator MCP server that performs arithmetic calculations and generates storytelling prompts using AI sampling capabilities.

OpenTelemetry-based observability SDK for AI applications

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

An another Node binding of llama.cpp

Simple evaluation tool for Claude Code. PASS/FAIL testing with LLM-as-a-judge simplified approach.

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

A Model Context Protocol (MCP) server for Tana

MCP server for integrating Turso with LLMs

A comprehensive, read-only, multi-tenant PostgreSQL MCP server with advanced schema introspection and query capabilities

A Model Context Protocol server for Vitest test execution and management

Use MDX to render high quality LLM prompts

mlld: llm scripting language

MCP server for My Scroll document editor - enables Claude to directly edit your documents with line-level precision

Prebuilt UI components for LLMAsAService.io

Native module for An another Node binding of llama.cpp (win32-arm64-vulkan)

A lightweight, framework-agnostic router for AI/LLM API requests.

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

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

CLI tool for managing vLLM deployments on GPU pods

A light and modern interface for Helicone's generateRouter API

A lightweight and fast markdown parser used by nlux that can be used to parse markdown text streams into DOM.

Node.js Library for Large Language Model LLaMA/RWKV

RecallioAI Memory node for n8n

Amazon Bedrock plugin for ElizaOS - integrates Claude, Titan, and other foundation models

Native module for An another Node binding of llama.cpp (linux-arm64-vulkan)

Qualifire client SDK

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

[](https://github.com/Galvanized-Pukeko/gaunt-sloth-assistant/actions/workflows/unit-tests.yml) [![Integration Tests](https://github.co

n8n community node for 302.ai AI service integration

'Slite MCP server'

⚡ 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.

Native module for An another Node binding of llama.cpp (win32-x64)

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

🚧 EXPERIMENTAL: OpenAI-compatible Cortensor provider for Vercel AI SDK - Actively in development

Use non-Anthropic models with Claude Code by proxying requests through the lemmy unified interface

Extract company logos

An MCP server implementation that integrates with yt-dlp, providing video and audio content download capabilities (e.g. YouTube, Facebook, Tiktok, etc.) for LLMs.

Workflow patterns for Grid LLM orchestration

A set of guards for LLM Apps

Native module for An another Node binding of llama.cpp (win32-arm64)

OpenInference utilities for ingesting Mastra spans

🧠 Intelligent API gateway with automatic model selection - connects Claude Code to 36+ LLM providers with smart task detection and cost optimization

AI-powered Super Agent, Super Prompts, and Super MCP nodes for n8n workflows

High-performance PDF text extractor (with OCR fallback) for Node.js, optimized for LLM pipelines. Uses PDFium, Tesseract, and C++ addon.

A minimalist LLM framework

Official JavaScript and TypeScript SDK for accessing SVECTOR APIs.

Lightweight CLI application for code agent interactions with LLMs

Deep Agents - a library for building controllable AI agents with LangGraph

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

Veas CLI - Command-line interface for Veas platform

CLI tool for installing opencode Agents configs from openmodes.dev

Official SDK for Magically - Build mobile apps with AI

Universal JSON data generator using LLM with configurable schemas

Universal protocol for knowledge management and project tracking systems - enabling seamless interoperability between platforms and AI assistants

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

Typescript bindings for langchain

Containerization Assist MCP Server - AI-powered containerization workflow tools for the Model Context Protocol

Native module for An another Node binding of llama.cpp (linux-arm64)

TVM WASM/WebGPU runtime for JS/TS

AI Agent Framework for building intelligent agents with LLM integration, function calling, and reflection capabilities

Model Context Protocol server for Mural visual collaboration platform

A library for adapting LLM models to different APIs

Backstage catalog backend module for MCP (Model Context Protocol) entities

A vite plugin to build vertesia UI plugins

MCP server for AI-powered code repository exploration through interactive storytelling

Obsidian Knowledge-Management MCP (Model Context Protocol) server that enables AI agents and development tools to interact with an Obsidian vault. It provides a comprehensive suite of tools for reading, writing, searching, and managing notes, tags, and fr

Real-time streaming AI consensus platform with HTTP+SSE MCP integration for Claude Code, VS Code, Cursor, and Windsurf - powered by OpenRouter's unified API

AgentForce Agent Development Kit - A powerful framework for building AI agents and servers

AI-driven development framework - conversational, simple, powerful

Native module for An another Node binding of llama.cpp (linux-x64)

🪨 Bedrock Wrapper is an npm package that simplifies the integration of existing OpenAI-compatible API objects with AWS Bedrock's serverless inference LLMs.

One MCP server to aggregate them all - A unified Model Context Protocol server implementation

Information on LLM models, context window token limit, output token limit, pricing and more

Turn any webpage intro structured data using LLMs

Unleash the power of 100+ specialized Claude agents for your development team via MCP

A comprehensive collection of essential and popular Node.js libraries bundled together for easy use in your projects.

A N8N community node to interact with a (custom) LLM model on an OpenWebUI instance.

AI SDK v5 provider for Claude via Claude Code SDK (use Pro/Max subscription)

A REACT-based lib that transforms JSON (or YAML) into interactive HTML markup.

Lightweight, composable LLM nodes for TypeScript

MCP server for running long-running AI tasks using @just-every/task

Interfaces for extending the embedjs ecosystem

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Agent Development Kit for TypeScript with multi-provider LLM support

MCP server wrapper for OpenAI's Codex CLI

Model Context Protocol (MCP) server that provides comprehensive SQLite database interaction capabilities

Native module for An another Node binding of llama.cpp (win32-x64-vulkan)

Model Context Protocol (MCP) server for Google Cloud Platform - Talk to your GCP resources

Public types, enums and options used by Llumiverse API.

An Eleventy plugin that generates llms.txt to expose site content to LLMs

An MCP server that provides expert-level consultation services for AI agents

A production-grade TypeScript template for building robust Model Context Protocol (MCP) servers, featuring built-in observability with OpenTelemetry, advanced error handling, comprehensive utilities, and a modular architecture.

LLM-driven RPG game server using MCP protocol

Model Context Protocol (MCP) server for running AWS Athena queries

JavaScript/TypeScript client for WordPress LLM Ready MCP endpoints

Enhanced MCP server for GPT-5 with advanced features

MCP server that provides hourly and daily weather forecasts using the AccuWeather API

Tiny, immutable, chainable Markdown builder for LLM prompts.

Model Context Protocol (MCP) server for Cerebras Code API integration with any MCP-compatible client. Run 'cerebras-mcp --config' for interactive setup.

Native module for An another Node binding of llama.cpp (darwin-arm64)

An MCP server that provides tools for checking Maven dependency versions

Multi-agent AI CLI wrapper with intelligent rotation, fallback, and conversation management

Unified XML Referring JSON Parser - Solve LLM JSON generation errors by separating complex content from JSON structure

CtxVM SDK for JavaScript/TypeScript

Security proxy for enterprise integrations for LLMs

Model Context Protocol (MCP) server for Bitbucket Cloud and Server API integration

Advanced routing and transformation system for Claude Code outputs to multiple AI providers

TypeScript SDK for Crawl4AI REST API - Bun & Node.js compatible

🧬 ModelMix - Unified API for Diverse AI LLM.

Universal Model Context Protocol Client - The complete toolkit for MCP

An MCP server for interacting with a Jenkins CI/CD server. Allows you to trigger jobs, check build statuses, and manage your Jenkins instance through MCP.

Shadowboxin: Utils for real-time streamed LLM-generated UIs.

NestJS module that auto-exposes your REST API as MCP tools via a single /mcp endpoint.

TypeScript MCP server boilerplate with STDIO and HTTP transport support, CLI tools, and extensible architecture

A TypeScript-native library that provides a unified interface for multiple LLM providers (OpenAI, Anthropic, Gemini)

MCP Tool to operate and integrate MongoDB Atlas projects into an AI developed project

Model Context Protocol (MCP) server for Google Cloud Platform - Talk to your GCP resources

The definitive all-in-one Model Context Protocol server for AI-assisted coding across 30+ platforms

MCP server wrapper for Google's Gemini CLI

A configurable AI chat interface component library

A super simple text splitter for RAG applications

Client library for MindStudio AI Workers

MCP server that wraps GNU GLOBAL(gtags) for AI coding agents to analyze codebases

MCP Server for Shopify API, enabling interaction with store data through GraphQL API

A simple JSON parser designed to handle malformed JSON from Large Language Models

A Node.js utility that quickly identifies files with uncommented code in your codebase. Designed for developers who want to efficiently tell LLMs exactly which files need comments added.

A translator's kit that uses the free APIs of Google Translate, Yandex, Bing, ChatGPT, and other LLMs

Native module for An another Node binding of llama.cpp (linux-arm64-cuda)

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

Experimental ModelFusion features

<div align="center"> <a aria-label="NPM version" href="https://twitter.com/dimitrikennedy"> <img alt="stream-hooks" src="https://img.shields.io/twitter/follow/dimitrikennedy?style=social&labelColor=000000"> </a> <a aria-label="GH Issues" href="h

Payloop JavaScript SDK

FluxAgent - 一个可灵活插拔的AI Agent系统框架，基于TypeScript开发，支持流式执行、事件系统、插件系统、知识库管理等功能 (Protected Release) (Protected Release) (Protected Release) (Protected Release) (Protected Release) (Protected Release) (Protected Release) (Protected Release) (Protected Release) (

MCP server for GitHub Enterprise API integration with Cursor, enabling AI access to repositories, issues, PRs and workflows

typescript ai utils

MCP server for OpenAI Codex CLI integration

A JSX-based templating engine for generating structured prompts with TypeScript support

A powerful JavaScript SDK for creating and managing teams of AI agents with dependency management, parallel/sequential execution, and memory capabilities.

Decentralized Memory Layer on Sei Blockchain

Unified registry for AI model providers and their metadata

Typescript bindings for langchain

A local CLI tool to explain source code using LLaMA models powered by llama.cpp

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

SowonFlow - AI-powered automation platform with intuitive YAML workflow definitions

A lightweight command-line AI code review tool that also provides general-purpose AI capabilities

Search, create, and retrieve tasks, add comments, and track time through natural language commands.

Unified LLM API with automatic model discovery and provider configuration

OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects

Locate JavaScript files with 'const' or 'process.env' usage in LLM-generated codebases

Use non-Anthropic models with Claude Code by proxying requests through the lemmy unified interface

MCP server for Sequential Thinking Tools

SDK for Hamming Evals Framework

Tiny helpers to extend Zod enums for open-set/iterative classification workflows.

Client-side MCP server for LLM clients

LF Widgets - Main components library

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

GigaChat integration for LangChain.js

Task - Thoughtful Task Loop

The AI Model Orchestrator - Intelligent multi-model workflows with device-locked licensing

A comprehensive Node.js library for AI Agents & LLM Integration, simplifying the creation of intelligent applications.

Enhanced MCP server for generating XMind mind maps - Independent version

ClickUp MCP Server for LLM integration

The **Runpod provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model and image generation support for [Runpod's](https://runpod.io) public endpoints.

Probe CLI binary for linux-x64

A lightweight TypeScript/JavaScript code indexer that generates comprehensive project maps for LLMs

Comprehensive MCP Server for Plane with 76 project management tools including custom properties, sub-issues, relations, and transfer operations

OpenTelemetry exporter for VoltAgent observability with Vercel AI SDK

Probe CLI binary for darwin-x64

Model Context Protocol server for Snowflake database integration

client library for asterai.io

This package helps you summarize pdfs using Gemini nano on edge or on browser, making it compliant safe, faster and free

Node.js/TypeScript MCP server for AWS Single Sign-On (SSO). Enables AI systems (LLMs) with tools to initiate SSO login (device auth flow), list accounts/roles, and securely execute AWS CLI commands using temporary credentials. Streamlines AI interaction w

MCP server and CLI tool for web search by OpenAI o3 model

Maxim AI JS SDK. Visit https://getmaxim.ai for more info.

Create a custom LLM project from scratch - like create-react-app for language models

Zero-dependency machine learning, AI, and data processing library for modern JavaScript

> Deobfuscate Javascript code using LLMs ("AI")

OpenInference instrumentation for AWS Bedrock

A system for transforming AI interactions from assumption-based guesswork to systematic, evidence-driven excellence.

Fast, token-efficient web content extraction - fetch web pages and convert to clean Markdown

Advanced LLM-powered JavaScript unminifier and deobfuscator

n8n community node for Future AGI prompt management with async logging, evaluation, and content protection capabilities

适用于任意前端框架的 AI 集成套件，支持多模型接入、聊天面板、Function Calling 等。

CLI tool for creating, running, and testing ADK agents

Autonomous AI cost protection that actually works. Real-time budget enforcement with auto-kill prevents runaway LLM costs before they happen. Unlike monitoring tools, AgentGuard stops the bleeding.

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

TypeScript SDK for tracing LLM, RAG, and agent applications with Noveum

Probe CLI binary for darwin-arm64

A TypeScript library for building dynamic AI-driven workflows with LLM planning and static flow composition using Effect

Useful util functions when extending the embedjs ecosystem

CLI tool for running AI prompts with structure and repeatability

tune - LLM chat in text file

AI Multi-Agent library for Javascript Developers.

Observee SDK - A TypeScript SDK for MCP tool integration with LLM providers

TypeScript client library for AI Search API - search and retrieve intelligent responses with context awareness

Prototype MCP Server for CLL

Qualcomm lib Genie binding for React Native

AI assistant MCP server with web search and code execution capabilities

Model Context Protocol (MCP) server implementation for Cloudflare Workers

Enhanced PostgreSQL MCP server with read and write capabilities. Based on @modelcontextprotocol/server-postgres by Anthropic.

LLM plugin for Bowl PayloadCms plugin

LF Widgets - Showcase component and documentation

A local MCP stdio server that provides access to the OpenAI (ChatGPT) API with web search capabilities for Claude Code and other MCP clients.

HOC and hook to use the LLMAsAService.io LLM load balancer and firewall

AI-powered QA agent using LLM models for automated testing and web interaction

AI CLI tool that generates Cypress test scripts from natural language scenarios and a URL

Interactive CLI tool and MCP server for managing MCP configurations with tech stack detection and recommendations

Zero-dependency, modular SDK for building robust natural language applications

Model Context Protocol (MCP) server for Google Gemini 2.5 Pro with conversation context management

Genetic-Pareto prompt optimizer to evolve system prompts from a few rollouts with modular support and intelligent crossover

Apple LLM provider for Vercel AI SDK

Advanced AI-powered JSON-LD schema utility with intelligent caching, lazy loading, and performance monitoring. Zero dependencies.

NAPI-RS bindings for BodhiApp server with integrated tests

Agent Development Kit for TypeScript with multi-provider LLM support

Enable usage of OpenAI models with embedjs

MCP AI调用工具，支持OpenAI规范接口，允许大模型通过MCP调用外部AI服务

The 4 fundamental AI operations for building intelligent applications

Intelligent LLM model selection with hybrid AI + deterministic scoring + Live Vellum scraping

React helpers for Composable AI

Typescript bindings for langchain

Mixer LLM Plugin module of the BOM Repository

Streaming-first structured data extraction from LLMs with real-time updates

Model Context Protocol (MCP) server for interacting with Node-RED

TypeScript implementation of MLflow Tracing SDK for LLM observability

Cross-platform probe code search tool (meta package)

Web page loader for embedjs

An MCP server implementing a scratchpad for LLM inner monologue

Собирает структуру проекта и содержимое файлов в Markdown для формирования контекстных подсказок (prompts).

Sync your local Task Master tasks to Notion, enabling powerful Kanban, timeline, and calendar views. Fork of claude-task-master with Notion integration.

An efficient task manager. Designed to minimize tool confusion and maximize LLM budget efficiency while providing powerful search, filtering, and organization capabilities across multiple file formats (Markdown, JSON, YAML)

A WASM-powered library to cap incomplete JSON streams.

Add AI functionality to your flows! This module includes a set of nodes that enable easy communication with Ollama, enriching your projects with intelligent solutions.