npm agents

Portable governance lifecycle and CLI for issue-first agentic SDLC

Agentic AI Library specialized in LLM Function Calling

Plan in detail. Execute in parallel. Blueprint is the agentic development framework that gives Claude Code, Codex & Cursor autonomous, structured execution across milestones, phases, and parallel streams.

JSON Schemas for the Agentic Commerce Protocol (ACP), vendored from the upstream Apache-2.0 spec at agentic-commerce-protocol/agentic-commerce-protocol (rev 2026-04-17). Bundles: agentic_checkout, cart, delegate_authentication, delegate_payment, discount,

n8n community node for Agentic Hub API integration - Unified node with all resources (projects, workflows, agents, content, conversations, messages, files)

Run Agentic Deploy agents on your local computer

Axle core runtime for building agentic LLM applications.

A2A (Agent-to-Agent) and MCP Express middleware for AI Agents using A2A, MCP, and the Agentic Profile protocols

Core functionality for agentic knowledge guidance system

emploke — orchestrate agentic systems built on the MetaAgents format spec

JavaScript implementation of the Crew AI Framework

Implementation of the AG-UI protocol for CrewAI.

Unofficial CrewAI JavaScript SDK

CrewAI tool definitions for GenZAgents work receipts — typed, signed, ready to drop into a Crew

Zero-config agentegrity adapter for CrewAI JS. Mirrors the Python agentegrity.crewai module.

CrewAI adapter for CodeSpar — convert session tools to CrewAI tool format

TypeScript port of crewAI for agent-based workflows

Community nodes for CrewAI integration

APort guardrails for CrewAI — task decorator / middleware

MCP server for CrewAI Enterprise — kick off, status, resume, and inspect crew runs from any MCP client (Claude Code, Cursor, Windsurf, 0nMCP). 50 free runs/month on the CrewAI free tier. Built by 0nORK.

CrewAI tool wrappers for PAS SDK

VerifiedState integration for CrewAI — cryptographic receipts for every agent assertion

AuthorityRail governance plugin for CrewAI. Wrap any CrewAI tool or task with ARES-v1 pre-execution certification.

Multi-agent automation framework written in TypeScript. Patterned after CrewAI.

ScopeBlind evidence wrapper for CrewAI tool calls. Automatically creates Veritas Acta receipts for every tool invocation and delegation.

AI agent orchestration framework for TypeScript/Node.js - 32 adapters (LangChain, AutoGen, CrewAI, OpenAI Assistants, OpenAI Responses, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw, A2A, Codex, MiniMax, NemoClaw, APS, Copilot, LangGrap

Framework-agnostic agent skill library. Drop-in skills for Claude Agent SDK, LangChain, OpenAI Assistants, CrewAI, AutoGen, Cursor, AGENTS.md-compatible tools (Codex/OpenCode/Antigravity), and any AI agent runtime.

CrewAI adapter for RANA Framework

HELM governance adapter for CrewAI JavaScript/TypeScript — task and tool governance

AI agent debugging, collaboration, and trace observability. Built for teams using CrewAI, OpenAI, and more.

Grounded Intelligence for AI agents. MCP server with real-time web search, evidence extraction, verification, and structured citations. The research infrastructure for LangChain, CrewAI, and custom agents.

CrewAI bridge for SwarmSync.AI — OpenAI function definitions, REST executor, and Python bridge snippet for using SwarmSync as CrewAI tools.

Thin CrewAI adapter for the OxDeAI universal execution guard

CrewAI tool for Ophir agent negotiation

Scaffold a DCP-AI governed crewai agent project

AgentFolio integration for CrewAI — agent identity, trust scores, and marketplace access

Zero-code runtime observability for JS/Python + AI agent debugging. Traces LangChain, CrewAI, OpenAI, Anthropic, Gemini. Eval, security, compliance, cost tracking. Free, local-first.

CLI for Xenarch — non-custodial x402 MCP server for AI agents. Claude, Cursor, LangChain and CrewAI pay HTTP 402–gated APIs with USDC on Base L2.

Bidirectional adapters between ai-agencee DAG format and LangGraph, CrewAI, AutoGen, and Semantic Kernel

Verra AI governance SDK: detection pipeline (PII, jailbreak, prompt injection, policy violation) with LangChain, CrewAI, AutoGen, LlamaIndex, and Semantic Kernel integrations.

Full Court Defense — real-time AI firewall and CLI scanner for chatbots, agents and RAG pipelines. Tool-call guards for MCP, LangChain, LlamaIndex, AutoGen, CrewAI and Semantic Kernel.

AgentGuard — runtime governance for production AI agents. APRA CPS 230, EU AI Act and ISO 42001 evidence built-in. Native OpenClaw, LangChain, CrewAI, OpenAI Assistants, AutoGen, and MCP integrations.

CrewAI integration for v402 paid tool access

Non-custodial x402 MCP server for AI agents. Lets Claude, Cursor, LangChain and CrewAI pay for HTTP 402–gated APIs with USDC micropayments on Base L2. Unlike Cloudflare Pay-Per-Crawl, works on any host and settles agent-to-publisher direct.

Open-source testing and regression detection framework for AI agents. Golden baseline diffing, CI/CD integration, works with LangGraph, CrewAI, OpenAI, Claude, HuggingFace, Ollama, and MCP.

CrewAI adapter for CoFounder Framework

Secure runtime for AI agents. Policy-enforced tool execution, secret blocking, audit trails. Drop into OpenAI, Anthropic, LangChain, CrewAI. Zero dependencies.

x402-paid MCP server with machine-executable REGISTER runbook at /.well-known/register-runbook.json — agents bid USDC on Base L2 to list themselves. LangGraph/CrewAI/Eliza/A2A agent-discovery + agent-marketplace.

Framework-agnostic agent observability & LLM tracing. Supports OpenAI, CrewAI, AutoGen, LangGraph, and OpenTelemetry.

Framework adapters for AriKernel — protect agents built with LangChain, CrewAI, OpenAI, and more

Model Context Protocol server for the SOTA marketplace — exposes register/sandbox/bid/deliver/payouts as MCP tools so autonomous agents (Claude Agent SDK, OpenClaw, LangGraph, OpenAI Agents SDK, Mastra, Pydantic AI, CrewAI, smolagents) can plug in without

Universal HTTP AgentRunner adapter for @pmcollab/coworkstream-engine. Wraps any agent reachable over HTTP — covers Python frameworks (LangChain Python, CrewAI, AutoGen, Google ADK, Semantic Kernel) and any custom backend.

The Parasitic Browser Bridge for CrewAI. Control authenticated Chrome sessions via MCP.

TypeScript SDK for autonomous AI agents — on-chain payments, reputation, marketplace on Base blockchain. Compatible with LangChain, CrewAI, AutoGen, Eliza, Claude MCP.

Create a DingDawg marketplace agent in under 5 minutes. Supports MCP native, OpenClaw, NemoClaw, LangChain, CrewAI, and custom frameworks.

Scaffold a prediction market agent project. Works with LangChain, CrewAI, OpenAI Agents SDK, or vanilla TypeScript.

Solana payment SDK for AI agents - supports OpenClaw, LangChain, CrewAI, and MCP

CrewAI-style role-based multi-agent team orchestration for Wundr

Tapal — universal mail MCP server. Plug into Claude Desktop, Claude Code, Codex, Gemini CLI, Cursor, Windsurf, Zed, Continue.dev, LangChain, CrewAI, AutoGen — and let any AI agent read, search, draft, organize, and triage your email. Apple Mail today; Out

Agent payment infrastructure MCP server. Give AI agents autonomous payment capability — stablecoin transfers, currency swaps, agent wallets, and fiat operations on Hedera. Works with Claude, LangChain, CrewAI, AutoGPT.

63-jurisdiction rental compliance skills for autonomous AI agents. OpenClaw, MCP, LangChain, and CrewAI compatible.

LangChain and CrewAI adapters for API Toll paid tools

MoneyGraph cross-border payment SDK — send payouts to 82+ countries via bank, mobile money, SWIFT, SEPA, ACH. Built for AI agents (Claude, ChatGPT, Cursor, Copilot, LangChain, CrewAI, Vercel AI SDK). Powered by StratosPay. Sandbox included.

AI agent governance platform — static scanning + runtime interception for Claude Code, Cursor, GitHub Copilot, Codex CLI, LangChain, CrewAI, and Kiro. Blocks dangerous tool calls in real-time.

Governance receipts for AI agents — DingDawg Loop Protocol (DDLP) for safe scheduled agents with governance gates, compliant with EU AI Act Art. 12, Colorado AI Act (SB 24-205), and NIST AI RMF. Every loop execution is verified, receipted, and fail-closed

Vigil compliance tools for AI agents — Vercel AI SDK, OpenAI, Claude, LangChain, and CrewAI

Seracade is a drop-in OpenAI-compatible routing proxy for AI agent teams. Six named capabilities: Call (every request, addressable and replayable), Step (sub-Call routing context inside agent trajectories), Quality Score (calibrated, version-stamped quali

TAMON — Task Automation & Management Operations Network. Self-hosted AI assistant framework powered by Claude Code.

<div align="center">

Smart installer for ACPrompt — one-shot MCP config for any agent harness.

AI Credit Card: Give your AI Agents autonomous virtual credit cards (Mastercard) via Stripe Issuing to pay for APIs and SaaS. x402 & MPP compatible.

**Build, run, and observe AI agent workflows.**

Crypto Card: Give your AI Agents autonomous virtual credit cards (Mastercard) via Stripe Issuing to pay for APIs and SaaS. x402 & MPP compatible.

AXIP MCP Server — connect any MCP-compatible agent to the AXIP agent marketplace, plus a one-call AI Readiness Audit tool for company-level auditing.

AgentCard: Give your AI Agents autonomous virtual credit cards (Mastercard) via Stripe Issuing to pay for APIs, SaaS, and cloud computing. x402 & MPP compatible.

MCP server giving AI agents instant access to permanent crypto exchange fee discounts (20-40% off). Affiliate revenue share for AI agent developers — your users save fees, you earn lifetime commissions. 6 tools: fee comparison, referral codes, country com

Matrix UI + proxy + coordinator stack — npx-installable on macOS and Linux.

Drop-in agent chat UI for Angular 20+. Headless primitives that read from a runtime-neutral `Agent` contract, plus opinionated compositions (`<chat>`, `<chat-debug>`, GenUI surfaces) you can ship in days.

AxonFlow SDK - Add invisible AI governance to your applications in 3 lines of code

CLI tool for scaffolding **Agent-User Interaction (AG-UI) Protocol** applications.

Launcher: installs the axonpush/skills bundle and runs the integrate orchestrator in your AI coding agent.

Qualixar OS: The Universal OS for AI Agents. One platform, every model, every framework, every transport.

Find the AI agents in your codebase. Zero config, zero dependencies. Just run npx arkna-scan.

Browser automation API for AI agents — structured page recon, form filling, clicking, and navigation via Chrome CDP

Drop-in Tessera integration for the Vercel AI SDK. One line of config routes generateText / streamText / generateObject / streamObject through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/an

Create a new AgentVoy project — npx create-agentvoy my-agent

Stealth browser for AI agents. Bypasses Cloudflare, DataDome, PerimeterX. Residential IPs from 10+ countries. iPhone 15 Pro fingerprint. Drop-in Playwright replacement — launchHuman() just works.

Official Taxida MCP server and developer toolkit for cab search, booking, and trip workflows.

Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required

AI-to-AI Assertion Marketplace — buy and sell verified attestations between AI agents to eliminate redundant compute

The local-first falsifiable decision ledger — MCP server that turns an Obsidian vault into a compounding decision system with multi-model AI council dissent and outcome-driven refutation propagation.

Drop-in Tessera integration for the Mastra agent framework. One line of config routes every Mastra Agent's LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Compatible with @ai-sdk/openai, @ai-sdk/anthropic, @ai-sdk/m

CLI tool to scan codebases for LLM SDK usage, AI frameworks, and exposed API tokens

Install PM Council — five AI strategists that argue about your product decisions — into Cursor or Claude Code.

Five governance questions for your AI agent system. Identity, restraint, accountability, memory, charter. Zero dependencies.

A node package for building AI agents

The runtime your AI agents deserve. Process management, memory bus, tool routing, message passing, and scheduling for autonomous agents.

OpenTelemetry SpanProcessor for atrib's verifiable action layer. Emits signed records from OpenInference-shaped spans.

RDF semantic graph layer for Meshpocalypse — SPARQL routing, JSON-LD/CRDT bridge, W3C PROV-O provenance, and AI framework adapters

Connect your agent to pre-computed market context that improves reasoning and reduces token usage.