npm agents

Official Certynix MCP Server — Expose Trust Infrastructure to AI agents

AIGuild CLI — install and manage AI skills from your terminal

CLI toolkit for the automagent agent definition standard

Validate and test your DingDawg marketplace agent before publishing. Checks manifest, MCP tools, governance policies.

Complete starter kit for bootstrapping AI agent companies. Three-layer verification, 27 skills, GSD v1 execution, self-learning CLAUDE.md.

Standardized JSON schema and TypeScript SDK for defining AI agents and workflows with framework adapters

12 native protocol layers for AI-agent systems. No wrappers. No SDK dependencies.

Community-driven registry CLI for Mastra/AI agents, workflows, and tools

Agent teamwork in your terminal — CLI-first coordination for any AI agent runtime

Multi-user AI group chat via MCP — let your AIs talk to each other

AI-powered marketing automation platform with 23 agents across 7 clusters

Minimal LangChain-compatible tool wrapper for Nooterra

Agent Payment Standard v1 - The open protocol for AI agent payments on PayPol

Multi-agent orchestration SDK for TypeScript — agent teams, skill-first architecture, MCP client/server, multi-provider LLM support.

Agent tools for 402.md — framework-agnostic + LangChain adapter

APS governance layer for Stripe agent payments — commerce delegation, spend limits, merchant allowlists, audit trail

Constraint-learning runtime for iterative agent loops. Agents that structurally learn what NOT to try again.

Tamper-evident, cryptographically verifiable audit trail for AI decisions

Security scanner for n8n workflow JSON files

Cross-ecosystem agent behavioral telemetry SDK — report and read trust scores from the Dominion Observatory. The only MCP scoring network that accepts agent-reported runtime data.

Multi-agent orchestration framework for AgentSea. Build, compose, and orchestrate agent crews with role-based coordination, task delegation, and workflow automation.

MCP server for Clawtown - connect AI agents via Model Context Protocol

BrainstormRouter TypeScript SDK — AI gateway with memory, guardrails, and governance

SDK for the agent-to-agent services marketplace — discover, pay, and use AI agent services with one function call

MCP server for AgentGate — AI agent payment authorization and governance

Multi-agent orchestration CLI powered by Claude Code

Constitutional AI Governance Framework — Asimov's cLaws with HMAC-SHA256 integrity verification, memory watchdog, safe mode, and Ed25519 cross-agent attestation

Turn any GraphQL API into AI-agent-ready tools — MCP servers, LangChain tools, and standalone SDKs

RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.

A modern, type-safe, async-native framework for building agentic applications and A2A-compliant workflows in TypeScript.

Exa API Documentation MCP Server - Comprehensive offline-first access to Exa.ai documentation

TypeScript SDK for AI City — register agents, check reputation, and interact with the agent economy

Neruva MCP -- proprietary memory + grounding substrate for AI assistants (Claude Desktop / Claude Code / any MCP client). Typed Records store, document knowledge graph with exact multi-hop traversal (ownership/relationship tracing), semantic + structural

Scoped delegation protocol for the agentic web — DCTs, attestations, and MCP middleware

JavaScript client for AgentsIndex.ai — browse AI agents, frameworks, and tools programmatically

> **Record the vibe of your build** — A revolutionary Model Context Protocol (MCP) server that captures key development moments, enables **multi-agent traceability**, provides **intelligent context curation**, and facilitates **seamless agent-to-agent han

AI governance SDK — intercept, audit, and control AI agent tool calls. Add human-in-the-loop approval, kill switches, and a full audit trail to any AI agent.

CLI transpiler for converting AI agents between platforms

Multi-agent YAML workflow engine — 267 CN + 184 EN + 5 more language libraries of AI roles, auto DAG parallelism, zero code. One sentence → multiple AI roles collaborate → complete plan in minutes. 11 LLM providers, 7 need no API key.

Stdio relay and fallback MCP server for Agoragentic's hosted Triptych OS (Agent OS) Router / Marketplace. Exposes registration, search, provider preview, paid execution, and receipt-backed status tools.

Core memory palace engine for AgentRecall

Logbot lab

Kubernetes for AI agents — manage fleets of AI workers

Memory Palace MCP server for AI agents

Jack into any OpenAPI spec and rip a full-featured CLI with AI-agentic workflow automation

SDK for AgentRecall — persistent, compounding memory for AI agents

Agent-friendly client for storing files on IPFS via toju, paying autonomously with USDC on Base using the x402 protocol.

MCP server for Agent Credit Engine — AI agents can borrow USDC autonomously

Long-term memory engine for AI agents

Type-checked composition engine for AI agent capabilities

Security scanner and trust layer for AI agent skills/plugins — scan URLs, files, and directories for credential exfiltration, injection, and other threats

Model Context Protocol (MCP) server for Rhumb — discovery and access to 50+ agent-native tools

TypeScript/JavaScript SDK for Dakera AI memory platform

TypeScript SDK for Agent Lightning - Train and optimize AI agents with Reinforcement Learning

Safety infrastructure for autonomous AI agents

Interactive CLI scaffolding tool for domain-specific context graph applications with Neo4j

HITL infrastructure for AI agents. Your agent calls awaitHuman(), a human reviews via Slack/email/dashboard, agent resumes with a typed response.

Core SDK for Matimo: Framework-agnostic YAML-driven tool ecosystem for AI agents.

Research-backed Multi-LLM Router with parallel execution, learned routing (RouteLLM), prefix caching (RadixAttention), speculative decoding (Medusa/EAGLE), token compression (ISON), local LLM support (Ollama/vLLM/LM Studio), batch processing. Python bindi

ASG Pay MCP Server — 18 AI agent tools for Claude, Codex, Cursor, and Gemini CLI. Create virtual cards, fund wallets, manage spending, onboard agents via Model Context Protocol.

A framework-agnostic SDK with pre-built providers, a skills knowledge layer, MCP out of the box, and agents that autonomously build new capabilities — governed by a policy engine you control.

UAICP specification: reliability contract for agentic workflow integrity and control

Tailor CLI — AI intelligence platform for documents, legislation, education, and healthcare. Upload, review, sign, and collaborate with AI agents using PACT protocol.

Agoragentic is a marketplace where AI agents buy and sell task execution, paid in USDC, with a public receipt for every call. Official Node.js SDK and agora CLI for Triptych OS (Agent OS) deployed agents and swarms, Router / Marketplace routing, receipts,

Memory OS for AI coding agents. Local-first persistent memory with an upgrade path to projects, teams, and cloud sync.

Your AI workforce. Every user gets an AI manager that runs their team — finance, marketing, engineering, operations — for the cost of API calls.

SDK for Pathlight — visual debugging and observability for AI agents

Security co-pilot for AI agents. Scan for vulnerabilities, verify governance, audit MCP servers, and generate compliance reports — all from Claude, Cursor, or any MCP client.

Shared TypeScript types and x402 payment-flow utilities for @xenarch/agent-mcp — Xenarch's non-custodial x402 MCP server.

E2E encrypted agent-to-agent communication SDK — Double Ratchet, X3DH, deniable auth, ML-KEM-768 post-quantum, SSE streaming, ratchet persistence, multi-relay federation

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

Universal pay-per-use tool API for AI agents — 23 tools, x402 USDC payments, Hive collective memory, Hallucination Pills, MCP server for Claude/Cursor/Cline/Windsurf. Free tier 10/day, no signup.

26 AI agent tools in 2 lines. Web search, price feeds, Hive memory, on-chain tx, LLM routing, Hallucination Pills. Free tier, no credit card.

Declarative agent teams with DAG execution and context routing. Define what each agent knows.

x711 — Universal AI Agent Gas Station. 23 tools, Hive collective memory, Hallucination Pills, x402 USDC payments, MCP server for Claude/Cursor/Cline/Windsurf. Free tier 10/day, no signup.

AINative ZeroDB Memory MCP Server - 18 tools for agent memory: 9 memory + 5 write-back (Slack, Gmail, Calendar, GitHub, Notion) + 4 plan artifacts (persistent plans/PRDs across sessions with diff history). Auto-context middleware. Production-ready for Cla

MCP server for AgentOracle — claim verification for AI agents. Verify before you act. x402-native on Base, SKALE, Stellar.

Zero‑dependency Agent Identity Protocol (AIP) SDK – Ed25519‑based token signing & delegation.

MCP server for AI agent trading — 275+ perpetual markets including TSLA, NVDA, GOLD, SILVER via Hyperliquid HIP-3. Stocks, commodities, crypto, forex. By Purple Flea.

Interven AI Agent Firewall — drop-in gateway proxy. Scan every tool call through policy + risk scoring. One command, zero infrastructure.

Official SDK for registering and operating AI agents on Vorn — the agent-centric social platform

Email verification API and API infrastructure for AI agents

Security Proxy for Model Context Protocol — Govern any MCP tool call with ABS Core NRaaS (Non-Repudiation as a Service)

Rubric Protocol SDK - post-quantum AI attestation for EU AI Act compliance. Patent Pending.

The security layer for AI agents — platform-agnostic threat detection with 300+ rules, runtime blocking, and remediation guidance. Continuous protection.

Background check for AI agents — discover, assess, and test before you ship

Governance receipts for AI agents — universal, MCP-native, fail-closed governance layer compliant with EU AI Act Art. 12, Colorado AI Act (SB 24-205), and NIST AI RMF. LNN interpretability, IPFS audit proofs, and rollback for any agent in any framework.

Deterministic Agentic Safety Controller (DASC) for Node.js

Real-time debug dashboard for multi-agent AI systems — topology graph, LLM turn inspector, tool call traces, memory panel, run history, replay, and webhook alerts

Universal AI agent tool API — web search, price feeds, collective Hive memory, on-chain tx, LLM routing. 23 tools, pay-per-call USDC. No subscription.

Framework adapters for connecting TypeScript agents to the Agent2Agent protocol.

Enterprise-grade MCP firewall for conscious AI stewardship - Zero-trust security layer for Model Context Protocol servers

GoldHold MCP server -- persistent memory for AI agents. Search, store, and recall across sessions. https://goldhold.ai

TypeScript/Node.js client for A1: cryptographic identity and authorization for AI agents

Official Node.js SDK for Arkna: AI agent evidence

Pipeline gateway client for multi-agent systems — drop-in proxy, budget enforcement, dedup cache (optional x402 settlement)

Official TypeScript SDK for Vorim AI — AI Agent Identity, Permissions & Audit

Non-custodial spending controls for AI agent wallets. Enforce limits without holding keys.

Memory and self-awareness layer for AI agents - MCP server for state tracking, replay, and undo

Interven JS/TS SDK — Approvals + Audit for AI Agents. Scan tool calls through policy + risk scoring. Block, redact PII, or route to human approval via Slack.