npm agents

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.

AI-native quality gate engine with local Bayesian learning. AST analysis, drift detection, Fix Packet generation, and agent self-healing across TypeScript, JavaScript, Python, Go, Ruby, and C#.

Release notes and changelog generation with LLM-powered enhancement and flexible templating

OpenClaw plugin — Agent communication + LLM cost tracking + telemetry reporting

Lightweight, composable agent orchestration for autonomous agents. Multi-agent primitives (spawn, defer, MCP meta-tools), single-gate governance via bareguard, cross-platform shell tools, MCP bridge. ~2.7K lines core, one required dep.

Schema processing utilities for Sanity Agent

ACP (Agent Client Protocol) server for DeepAgents - enables IDE integration with Zed, JetBrains, and other ACP clients

SEO and LLM optimization for Elyra -- audit, structured data, llms.txt, meta tags

Crash detection, auto-repair, and health monitoring for AI agent gateways. Watches your OpenClaw or Hermes gateway, detects crashes, runs instant local repairs, and reports to Agent Hospital for AI-powered diagnosis.

Extract & validate JSON from messy LLM output. Designed for Claude / Codex CLI workflows where tool-use is unavailable. XML-tag aware, with multi-stage fallbacks and jsonrepair.

General-purpose agent with transport abstraction, state management, and attachment support

LLui Agent bridge — MCP server that translates Claude Desktop tool calls to LLui apps via LAP

AI-Powered Content Translation for Strapi with Batch Translation Support. Forked from strapi-llm-translator by grenzbotin.

VAT development agents - dogfooding the vibe-agent-toolkit

Framework-agnostic AI agent tool definitions for the Lombard protocol

A React hook wrapper for Agent Handler Link.

Nuggets identity verification toolkit for LangChain.js

A simple agent for performing a sequence of http requests in node.js

MCP (Model Context Protocol) adapter extension for Pi coding agent

Transport/proxy runtime seam for agent-mux launcher bridging

Repository containing the LangchainJS toolkit for creating powerful web3 agents.

Generic agent harness — domain-agnostic loop strategies + LLM provider abstraction. Source for both @agent-devtools and external SaaS consumers.

## Installation

Initialize Neon projects

Type definitions for Sanity Agent

MCP server for n8n with tools for generating workflows, linting, diagnosing failed executions, and driving live n8n instances. Built for AI agents.

OCI NodeJS client for Compute Instance Agent Service

Agent instrumentation SDK for forensic auditing — auto-signing, hash-chaining, LangChain adapter

Plannotator Pi extension - interactive plan review with annotations, annotate agent messages, and review code/PRs

LangChain TypeScript SDK - Human-in-the-Loop validation via Loopman platform

connect any ai agents to solana protocols

n8n community node for DeepSeek chat models (Pro / Flash) with reasoning_content (Chain-of-Thought) support, usable as a LangChain sub-node inside the AI Agent and Basic LLM Chain.

Agnostic runtime CLI for session-lifecycle workflows. Auto-detects namespace from any `.<ns>/sessions/` dir in CWD; falls back to 'agent-workflow'. Bundles the universal `agent-workflow` skill (35 skills + 17 commands + 7 hooks template) in the tarball —

Agent run-loop primitive over Tangle sandbox transports — runs an AgentProfile against a brief with criterion gates, budget caps, and streaming events. Includes TangleToolProvider for Pi tool integration.

AI coding agent harness and local dashboard for Claude Code, OpenAI Codex, Google Antigravity, and GitHub Copilot - setup audits, guardrails, structured skills, deny hooks, and persistent learning loops.

> Your AI financial assistant for Celo MiniPay. Chat to send stablecoins, check balances, or learn about Celo — every action is an on-chain Celo transaction.

SEED Lab research-agent operating system for OpenCode

Authentication provider for Cursor, extracting credentials from local environment or agent.

Claude Code GUI for parallel AI coding — drive Claude (default), OpenAI Codex, DeepSeek, Kimi, or local Ollama in tabs. Multi-project sessions, terminal, browser & DB bubbles, code review, slash modes. Local-first, MIT.

Official Claude Code CLI — AI-powered coding assistant

MCP server for inter-Claude-Code session communication bridge

Tau - multi-provider AI coding CLI with Firecrawl-hosted WebSearch. Firecrawl offers 1k searches/month on free trials; just enter your API key.

SnapAgent - The lightweight, snap-in AI agent SDK. Multi-provider support. Edge-runtime compatible.

Telegram daemon for Claude Code that preserves the OpenClaw per-chat session model. Migration path for OpenClaw users moving to Claude Code.

Use Aerostack workspace tools as OpenAI function-calling tools

Local connector that links agent harnesses (Claude Code, Codex, OpenClaw, opencode, Pi) to the Ticlawk mobile app.

Claudio — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)

MCP server for Q402. Gasless USDC/USDT/RLUSD/Q payments on 12 EVM chains (USDG on Robinhood Chain), Q402 Yield (gasless supply and withdraw into Aave, Lista, and Morpho lending vaults), gasless non-custodial escrow (create, fund, release, refund, dispute)

Generate random mock data from OpenAPI descriptions for msw.

Turn GitHub Copilot into an OpenAI/Anthropic-compatible server with Claude Code and Codex support.

TypeScript SDK for running autonomous agent sessions across providers (Anthropic, OpenAI, DeepSeek, Gemini, Mistral) behind one interface.

MoltConn MCP server — connect AI agents to the autonomous agent marketplace

One-command autonomous agent registration on Agent Coliseum. Mints a free-tier credential, solves the PoW challenge, writes the MCP config into your Claude Desktop / Cursor configs. Zero clicks, zero wallet.

Terminal-native autonomous coding agent powered by free AI models

PARALLAX ENGINE plugin for OpenCode -- protocol enforcement, friction-loop verification, mode switching (plan/build/debug/horizon), trace recording, coherence scoring, CI gate, PR-ready trace artifacts, and autonomous long-horizon supervision

Governance-first recursive cognition infrastructure — LuisCore Chorus Field MCP client + agent CLI (bootstrap, post, feed)

Public Preview — AgentOS GitHub Copilot Extension: Build safe AI agents with natural language and 0% policy violations

Autonomous build pipeline with mechanical enforcement for Claude Code projects

Your Personal Web3 Assistant

Loxia AI Agents System - No-code/vibe-code/companion-coder platform

MCP server for Cascrow — AI-verified milestone escrow on the XRP Ledger

Structural code intelligence and persistent memory for AI coding agents, served over MCP (Claude Code, Codex).

Giga Bot — Gignaati's autonomous AI agent platform. Build, deploy, and run AI agents 24/7 with a two-layer architecture: Next.js Event Handler + Docker Agent. India-first, edge-native AI.

MCP server for iOS Simulator and Android Emulator control

An AI-powered terminal coding agent with perfectly designed Claude Code-style TUI, interactive model selection, and prominent model display that helps you write code faster, manage files, and execute commands

Governance substrate for AI coding agents — adversarial PR review, drift-detected rules, tamper-evident audit, and closed-loop outcome routing for Claude, Codex, Gemini, and OpenCode

Personal collection of Claude Code skills and agents, installable via `npx skills`.

The official TypeScript library for the Tambo AI API

Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action

Utilities to help with endpoint resolution

This library was generated with [Nx](https://nx.dev).

placeholder for @ant-design/x-sdk

GeneXus 18 MCP server — read, edit, and analyze GeneXus knowledge base objects (transactions, web panels, procedures, SDTs) directly from Claude, Cursor, and other AI agents over the Model Context Protocol.

Custom Jest matchers for AWS SDK v3 Client mock

<div align="center"> <img src="https://storage.googleapis.com/hume-public-logos/hume/hume-banner.png"> <h1>Hume AI TypeScript SDK</h1>

The **[Prodia provider](https://ai-sdk.dev/providers/ai-sdk-providers/prodia)** for the [AI SDK](https://ai-sdk.dev/docs) adds image model support for the [Prodia API](https://docs.prodia.com/).

Multi-channel AI gateway with extensible messaging integrations

nSure web client sdk

Actions SDK Fulfillment Library for Node.js

AWS credential provider that sources credentials from known environment variables

An isomorphic client library for the Azure Translator Service

CLI companion for PkgSeer - package intelligence for developers and AI assistants

AI-powered CLI for Seqera Platform - bioinformatics workflow management

MCP server for Scaly - connect AI assistants to your cloud infrastructure

<div align="center"> <img src="https://user-images.githubusercontent.com/6267663/230025738-42a4980e-a5ea-4d00-a591-65e8de14de85.png" width="200"> <h1>Leonardo Typescript SDK</h1> <p>The API for creating stunning game assets with AI.</p> <a hre

Offline-capable AI virtual assistant client with local RAG fallback and agentic capabilities for AsterMind

JavaScript library for using the Sapling.ai API.

Node.js SDK for LINE Messaging API

The official TypeScript library for the Mux API

Socket MCP server for scanning dependencies

Add Siri like features to your app

[](https://www.npmjs.com/package/@aws-sdk/middleware-expect-continue) [](http

Twilio's JavaScript Voice SDK

Arcjet runtime security SDK for Next.js — bot protection, rate limiting, prompt injection detection, PII blocking, and WAF

Fast, minimal Node.js wrapper for the Voids API AI chat completions.

Microsoft Application Insights JavaScript SDK - Web Basic

mcp-ui Client SDK

Project Integration Orchestration — multi-agent workflow protocol for vibe coders

Multi-agent system — multiple Claude Code instances collaborating via messaging

Multi-agent SDLC harness with knowledge graph, quality gates, and swappable LLM backends