Source
npm agents
7,970 AI agents indexed on MeshKore from npm. Agent packages published to the npm registry for JavaScript and TypeScript. Each entry links back to its package page.
7,970 agents · ranked by popularity · refine in the directory →
Source platform: npm →
npm agents — page 65 of 80
Official React Web UI for nxtlinq AI Agent — drop-in chat widget
AI Agent data collection & security analysis gateway (TypeScript)
CrewLoop AI agent skills bundle and CLI
React Web headless SDK for nxtlinq AI Agent — hooks and browser ports
CLI tool for managing AI agent rules across projects
交互式扫描项目并生成可追溯的 AI Agent 项目规则
Bridge WeChat to any ACP-compatible AI agent
agent-finance: AI-agent-first market intelligence CLI for evidence-driven financial research.
Page-attached AI Agent chat widget — one script tag, full agent experience.
Local-first AI agent runtime with a gateway, operator console, and CLI.
CLI to manage AI agent configuration files across Claude and Cursor platforms
Configurable AI agent plugin: pluggable providers/tools/memory with store-fs-backed conversation persistence
Install SkillBazaar skills into your AI agent
Shell CLI that lets ANY LLM agent call UTCP tools via code mode — discover tools, run TypeScript tool-chains in a sandbox, and complete interactive OAuth logins. No MCP required. Built for sandboxed agents (e.g. Claude Cowork).
General-purpose agent with transport abstraction, state management, and attachment support
Give your OpenClaw agent lasting memory: structured facts, semantic search, auto-capture & recall, decay, optional credential vault. Part of Hybrid Memory v3.
General-purpose agent with transport abstraction, state management, and attachment support
Runlayer Hooks TypeScript SDK
LangChain integration for HyperspaceDB
Decorators for provider collaboration and modern LangChain task patterns in NestJS.
LangSmith extension for Pi Coding Agent
LangGraph decorators and discovery integration for NestJS.
AgentPM™ Node SDK
VAT number validator for AI agents. EU VIES, AU ABR. Fraud risk scoring and name cross-check. PROCEED/HOLD verdict before any invoice payment.
Web search, URL fetching, GitHub repo cloning, PDF extraction, YouTube video understanding, and local video analysis for Pi coding agent. Supports OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, SERPdive, Kagi, Ollama, AnySe
Production utilities for the OpenAI Agents SDK — conversation persistence, tool caching, handoff tracking, tracing export, and guardrail presets
Vela — an agentic AI coding assistant for your terminal
Codebase memory for AI coding agents. Natural language preflight, graph viewer, and agent history in one command.
AI Setu client — drop-in OpenAI SDK with workspace credit accounting and multi-provider routing.
Enhance your Node-RED projects with advanced AI capabilities.
`HarnessV1` adapter backed by [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk), which drives the `codex` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l
Knowledge files, examples, and validation for Directive — the constraint-driven TypeScript runtime.
Architecture rules your AI coding agent can't ignore. It gets the rules for a file before it edits, and every change is checked — by a free local script or an LLM reviewer — before it moves on. Works with Claude Code, Cursor, Copilot, Codex, Cline.
✦ Polaris Agent — Navigate Complexity with AI. Autonomous Agent Framework with OODA Loop, MCP, A2A.
MCP security trust-check server for autonomous agents: safe install decisions, risk signals, controls and alternatives before installing MCPs, Skills or tools.
Aura Code — model-agnostic AI coding agent. Praktess framework.
Autonomous AI coding agent pipeline with quality gates, fresh context per batch, 79 community lessons, and compounding learning for Claude Code
Open Gateway Protocol (OGP) - Peer-to-peer federation daemon for OpenClaw AI gateways with cryptographic signatures
Minimal project memory and validation harness for AI coding agents.
Multi-provider CLI chatbot with autocomplete command suggestions
Local-first, MCP-compatible coordination plane for autonomous coding agents
_This package is **experimental**._
The **OpenTelemetry integration** for the [AI SDK](https://ai-sdk.dev/docs) collects tracing spans for AI SDK calls and sends them through your configured OpenTelemetry setup.
`HarnessV1` adapter backed by [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk), which drives the `claude` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSo
Run AI SDK agents in a terminal UI.
The AnyRouter provider for the Vercel AI SDK — call every AnyRouter model through `createAnyRouter`.
`HarnessV1` adapter backed by [`@earendil-works/pi-coding-agent`](https://www.npmjs.com/package/@earendil-works/pi-coding-agent). Pi runs in the host Node.js process and uses the sandbox as a remote filesystem + shell — no bridge process is installed insi
_This package is **experimental**._
<div align="center">
Agent framework for building autonomous actors in the SMRT ecosystem
Core AI agent framework with standardized collections, object-relational mapping, and code generators
Catalog-native TypeScript agent framework (Plasm CGS/CML, Vercel AI SDK, Nitro-oriented)
A lightweight TypeScript agent framework with OpenAI-compatible model providers, Zod tools, state stores, and streaming events.
Upstash AgentKit adapter for the Vercel Eve agent framework: memory tools, Redis-Search tools, a rate-limit gate, an Upstash Box sandbox backend, and cached tools.
Local runtime package for Agentic workspaces
EPIQ - ergonomic, distributed CLI-first issue tracker TUI ready for the agentic era
eex — self-runnable agentic platform cli
A-MEM agentic memory backend for OpenClaw — TypeScript rewrite
AI Builder OS primary package for executable, verifiable agentic builder workflows
Small primitives for the agentic web. AI-native UI framework.
A leaderboard for your agentic-coding token usage — race your friends, not strangers.
TypeScript SDK for building agentic AI applications — sessions, tools, providers, and context management
RVM (Agentic Virtual Machine) host adapter for agent-harness-generator — hardware-isolated deployment via capability tokens
Reference TickTick adapter for Agentic Task System. Wraps TickTick OpenAPI v1 + qdrant + ollama (nomic-embed) into the ATS adapter contract.
Agentic systems specialist agent for Bluetemberg — agent memory design, state management, orchestration patterns.
Install AGENTS.md and .agents/ configuration for Canonical Workshop projects
Command-line interface for Agentic Task System. Routes to the configured storage adapter and exposes find / get / url / links / hybrid / similar / create / update / bench.
Model-independent agentic benchmark harness for WrongStack (Aider polyglot + SWE-bench Verified) with deterministic graders and harness fingerprinting.
Local-first command center for agentic engineers.
Reusable primitives for building agentic harnesses (Claude Code runners, git/github adapters, composer steps, multi-model review).
Micro-agent core — the minimal loop that makes agentic behavior possible
Cross-platform Terminal CLI + TUI that hosts a local server so AI agents can connect via a pairing code and respond directly in your terminal. Works on Windows, Linux, macOS, and Android (Termux).
Persistent memory infrastructure for AI agents - Memory that adapts. Intelligence that compounds.
Track AI agent costs, tokens, runtime and spending. Prevent runaway OpenAI, Anthropic, LangGraph and OpenRouter agents from exceeding budget.
The model-independent trust layer for AI agents: verifiable identity, model provenance, tamper-evident SHA-256 audit chains, policy enforcement, and outcome verification. Framework-agnostic.
Node.js SDK for the BEACON Protocol - Agent Safety Layer
Detect and rebut rationalization patterns in AI agent output
AI Agent runtime — Harness Agent architecture + Agentic Loop engine
HarmonyOS programming development AI agent
DWF AI Connector - AI Agent console for DWF low-code platform
Governance, proof, and intelligence controls for AI agent fleets.
A Vite+ oriented, AI Agent friendly front-end toolchain
n8n community nodes for the ConfirmX WhatsApp Business Platform Public REST API. Ships a Message node (start conversation with a template, send text/media) and a ConfirmX AI Agent node, both eligible as AI Agent tools via n8n's usableAsTool.
Local-first, AI-agent-safe developer secrets manager (CLI).
Lightweight AI Agent Runtime for Node.js
AIAIAI Chain Agent — Solana-native AI agent for decentralized AI governance. Ticker: $AIAIAI
RankMySEO AI agent tools and MCP server
Behavioral transaction risk SDK for crypto wallets and AI agent wallets
Terminal client for Elsa AI Agent
Forge persistent memories for your AI agent. 9 MCP tools + 5 auto-engines. Powered by Shelby decentralized cloud.
Interactive terminal UI for exploring AppThreat atom files with AI agent
Self-healing browser QA: natural-language scenarios verified by an AI agent, replayed deterministically in CI
AI agent production gate: kill demos and turn them into production-deliverable systems
UniPost CLI for developer quickstarts and AI agent operator workflows.
CLI installer and reporter for Agent Blocked AI agent escalation alerts.
Platform abstraction layer for Svton AI Agent
TypeScript SDK for Gopher Orch - AI Agent orchestration framework with native performance
AI Agent Skills framework — Spec-Driven development with directed-graph rollback and quality gates
A monorepo dev toolkit — task runner, remote caching, security scanning, git hooks, and AI agent integrations — powered by @visulima/task-runner
Local-first CLI for recording and replaying repeated AI-agent workflows.