npm agents

AI Agent Orchestrator - Manages agile software development teams of AI agents

Message routing and orchestration for AI agent squads

Install and update kkAuto AI-agent skills and MCP config.

Drive the Kodena API from any MCP-capable AI agent.

Maroo Agent Wallet Stack — MCP server for AI agent wallet management on Maroo chain

Agent evaluation framework with LLM-based grading for AI agent quality assessment

Toolkit for testing and evaluating AI agent skills

ONE Agent - AI agent with a code execution RAS.

Drop-in AI agent controlled via Telegram, sandboxed to its folder

Chisiki Protocol SDK — AI Agent-native knowledge marketplace on Base L2. Register, trade knowledge, earn CKT rewards.

Kodwai CLI — AI-agent coding challenges and interview sessions

AI agent platform for ClawBridge Agency, powered by OpenAI Codex. Self-hosted, secure, customizable.

Phase 2 of the catalog plane. Adds vector embeddings, AI-agent access patterns, and the MCP server scaffolding on top of the Phase 1 foundation in `@voyantjs/catalog`.

Built-in agent-core runtime and tool surface for Babysitter.

Platform-agnostic nxtlinq AI Agent core — API client, types, and orchestration ports

P2P Agent Capability Sharing Protocol — Airbnb for AI agent pipelines

MCP server for VantagePeers — shared memory, messaging, and task coordination for AI agent teams

AI Agent Hub MCP Server

On-chain governance for AI agent swarms. Powered by Algorand.

The Universal Hub and Multiplexer for AI Agent MCP Servers and Skills

Argus — a terminal LLM agent (prebuilt Go binary via npm).

Umbrella package for recording, replaying, inspecting, and forking LLM-agent runs.

OpenTelemetry GenAI utility for standardized telemetry collection across LLM, Agent, Embedding, Tool, Retrieval, Rerank, Memory and more

Dependency-free AgentRewind core runtime for deterministic LLM-agent record, replay, and fork.

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

OpenApe agent runtime: per-agent process that connects to chat.openape.ai, runs the LLM loop with tools + cron tasks, and streams replies back to owners.

Give pi a mind: portable, self-maintaining memory for pi-coding-agent. Memory is passive — writes are explicit (remember_this / observe), retrieval is hybrid (vector + FTS5 + KG). Ships ask-first skill authoring (create_skill / update_skill).

Node-RED sidebar plugin for chatting with LLMs (Ollama / OpenAI / Custom OpenAI-compatible endpoints), generating flows, and importing results

Cisco IOS automation agent CLI with mock simulation, guardrails, and LLM tool-calling support.

Extentos MCP server — deterministic tools for building smart-glasses apps with AI agents.

Tembory Memory node for n8n AI Agents with profile, tools, timeline, graph and semantic memory

Command-line interface for Firecrawl. Scrape, crawl, and extract data from any website directly from your terminal.

ESLint rules that catch the patterns LLM agents get wrong — and teach them to self-correct

OpenAI-compatible LLM worker bridge for meego-harness WorkerServerSDK

Apps Machine — Selection Agent. Ranks app opportunities globally via dual-store (Apple App Store + Google Play) scraping, heuristic scoring, and Claude judges. Run `npx @apps-machine/selection-agent demo` for a 30s magical moment.

Hosted runtime for frame datasets. Managed wallet + tool catalog injection. Billed via x402 / MPP. Implements frames-cloud Tier 3 #15.

Installable oper8r Agent Skills for MCP clients, Claude Code, Codex, and Cursor.

Proactive cognitive AI assistant — learns your interests, pushes insights, evolves skills autonomously

Core toolkit for LangGraph.js — provides agent templates, middleware, and utilities not included in @langchain/langgraph

LangChain adapter for cdr-kit — getLangChainTools(agent).

GoodVibes personal operator assistant TUI with a proactive Agent product brain, isolated Agent Knowledge, local profiles, routines, skills, personas, and explicit build delegation.

Readonly technical support agent for Xuda Network mentors. It can inspect /var/xuda on the dev server through Codex with strict safety limits.

Event trigger normalization, enrichment, and filtering helpers for automation actions

CLI for roy-agent - Non-interactive command execution

TrackJS Error Tracking agent for NodeJS

Local agent for Orquesta - connects your VM to the Orquesta dashboard

LangChain.js integration for PubMed API - search biomedical literature and retrieve article metadata

Universal MCP server for 8+ AI platforms. Connects Claude, Cursor, VS Code, Windsurf, Zed, Codex, and Gemini to 298+ AgentPMT tools.

Skill Arena — benchmark skill effectiveness with controlled-variable comparison

pi extension that exposes agent-browser as a native tool for browser automation

LangChain adapter for the Agent2Agent protocol.

Yandex integration for LangChain.js

LangChain integration for cascadeflow - Add intelligent cost optimization to your LangChain models

LangChain.js integrations for Google Cloud SQL for PostgreSQL

Turn failed AI coding-agent runs into reusable AGENTS.md rules, SKILL.md files, and eval evidence.

> 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.

A starter for creating a TypeScript package.

OpenAI provider adapter for Anvia.

Runtime that enforces the OpenWar framework: phase-aware agent loop with confirmation, blocker, and destructive-action gates.

Run AI coding-agent CLIs inside a Docker sandbox scoped to the current project.

AI-powered code review CLI for git changes

Co-creation infrastructure for humans and code agents — visual environment, skills, continuous learning, and distribution.

JSON-RPC server that exposes Claude Agent SDK to any client (codex app-server compatible wire protocol).

> **Warning** > This is an experimental package. It is not maintained and the API is not stable.

Modified openai-node sdk by @cherrystudio

Unified LLM API with automatic model discovery and provider configuration

Cross-agent permission policy specification for AI coding agents

Zero-config CLI to use any open-source coding agent with TokenMix as the unified LLM backend.

An unofficial OpenAI Codex CLI fork with PromptPilot prompt enhancement.

Blaxel SDK for TypeScript

AggRoot - AI Assistant (Node.js/TypeScript Version)

QuickJS-backed code mode tool for AI SDK

Atoms Widget SDK for React applications

OpenTelemetry Tracing

AI apps orchestration plugin for the CE.SDK editor

NDK - Nostr Development Kit. Includes AI Guardrails to catch common mistakes during development.

Enterprise-grade MCP server for live docs, best practices, code audit. Context7 alternative — 445+ libraries, smart dispatch (use gt mcp), plain-text intent routing, telemetry, SSRF-hardened multi-source fetcher, atomic disk cache, IPv6 + Unicode-homoglyp

AI integration package for SuperDoc

Babysitter Codex skill bundle and integration package for OpenAI Codex CLI with SDK-managed process-library bootstrapping, 15 orchestration modes, and BOM-safe SKILL installation

Multi-channel AI gateway with extensible messaging integrations

CLI coding agent for complex agentic workflows and long-horizon development. Local models (llama.cpp / Ollama), BYOK across 17 providers, parallel agents, persistent memory, scanned skills.

A MCP server for GitLab

Node SDK for Scrapeless AI

React components and runtime for building Timbal chat and studio apps

`gs-ai-assistant` 是从 `main` 主分支迁出的 AI 助手能力工程。

Multi-agent AI assistant with local LLM inference

External cryptographic step ledger for long-running multi-agent orchestration

Multi-Agent Orchestrator System — docker-compose for AI coding agents

Multi-agent orchestration for GitHub Copilot CLI. 19 agents, 59 skills, parallel execution, HUD, PSM, SWE-bench.

MCP server + portable captain skill that turns any AI coding CLI into the orchestrator of a worktree-isolated multi-agent crew

Multi-agent orchestration framework for educational content creation

RabbitMQ channel plugin for OpenClaw with multi-agent async collaboration and topic subscription support.

Wander AI Auto Dev Config: A dual-mode interactive CLI and compliant Model Context Protocol (MCP) server for multi-agent development teams.

Multi-agent pipeline orchestrator for OpenCode — 7-gate autonomous execution

Persistent shared memory for multi-agent teams — append-only writes, relevance-weighted reads, TTL pruning, context injection

Maximum continuous integration for multi-agent coding — every edit is committed and pushed to trunk immediately

The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows.

Build your own multi-agent harness: typed toolkit for authoring plugins (skills, agents, commands, hooks) and shipping them to Claude Code and Codex from a single source tree.

The reference SDK for the Akashik Protocol — shared memory and coordination for multi-agent AI systems.