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 8 of 80

agent-searchkit

Local-first SearXNG search + reranking + research pipelines for AI agents. Framework-agnostic.

@micuintus/llm-wiki

As minimal as Pi. Karpathy's LLM Wiki pattern as a minimal, agent-agnostic skill.

@nathapp/nax

AI Coding Agent Orchestrator — loops until done

oh-my-opencode-slim

Lightweight agent orchestration plugin for OpenCode - a slimmed-down fork of oh-my-opencode

@cleocode/core

CLEO core business logic kernel — tasks, sessions, memory, orchestration, lifecycle, with bundled SQLite store

llamaindex

<p align="center"> <img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" /> </p> <h1 align="center">LlamaIndex.TS</h1> <h3 align="center"> Data framework for your LLM application. </h3>

circle-ir-ai

LLM-enhanced SAST analysis built on circle-ir

agent-comms

Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and real-time push delivery over TCP

@framers/agentos

AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.

@llm-ui/react

Display language model outputs in your React project.

@rozenite/agent-shared

Shared types and utilities for Rozenite agent packages

@cline/agents

Browser-safe agent runtime for the next-generation Cline SDK

@osohq/langchain

Oso integration for LangChain agents

@vibe-agent-toolkit/agent-schema

JSON Schema definitions and TypeScript types for VAT agent manifest format

@earendil-works/pi-coding-agent

Coding agent CLI with read, bash, edit, write tools and session management

@mammoth-protocol/mcp-server

MCP server for Mammoth Protocol. Makes Mammoth callable as a native tool for any LLM agent — Claude, GPT, Gemini, Eliza, Virtuals, and more.

@allurereport/plugin-agent

Allure Agent Plugin – AI-friendly markdown report generator

@vurb/swarm

Federated Handoff Protocol for Vurb — SwarmGateway B2BUA, multi-agent orchestration, zero-trust delegation, and upstream MCP client tunneling.

jat-feedback

Embeddable feedback widget for bug reports and feature requests. Captures screenshots, console logs, and user context as a web component.

@t2000/engine

Agent engine for conversational finance — AISDKEngine (wraps Vercel AI SDK v6 `streamText`) with 26 tools (18 read, 8 write), 12-guard runner across 3 priority tiers, silent intelligence layer, streaming, canvas, BlockVision-backed pricing. Chat-first by

@stripe/agent-toolkit

The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.

@threadwell/agent-core

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

@dreb/agent-core

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

@hanzlaa/rcode

rcode — the AI team that never forgets. Persistent memory, specialist agents, and slash commands for AI IDEs. Works in Claude Code, Cursor, Gemini, VS Code, and Antigravity.

@t2000/cli

Agent Wallet for AI agents on Sui — gasless USDC + USDsui sends, Cetus swap, MPP paid API access, MCP integration, scriptable from any shell.

@remnic/core

Framework-agnostic Remnic memory engine — orchestrator, storage, extraction, search, trust zones

@polkadot-agent-kit/llm

SDK LLM for Polkadot Agent Kit

@diabolicallabs/agent-sdk

Cost-tracking middleware for @diabolicallabs/llm-client. Async fire-and-forget ingestion to Agent Spend Dashboard. © Diabolical Labs

bowser

Lightweight browser detector

@amplitude/ai

Amplitude AI SDK - LLM usage tracking for Amplitude Analytics

@postman/tunnel-agent

HTTP proxy tunneling agent.

@helios-agent/pi-agent-core

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

@kognai/run

Run a Kognai agent from your sovereign vault — npx @kognai/run <agent>

miii-cli

The local-first autonomous coding agent. Claude Code UX powered by Ollama. Zero cost, maximum privacy, fully offline.

@ironbee-ai/cli

The CLI for IronBee — Verification and Intelligence Layer for Agentic Development

@zosmaai/dhara

Minimal, secure, language-agnostic AI coding agent harness. Agent loop, extension protocol, 20+ LLM providers, session persistence, and TUI/REPL.

acpx

Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line

@sogni-ai/sogni-intelligence-client

Public Sogni Intelligence client — Node.js convenience wrapper for the Sogni SDK plus the public-safe subset of @sogni/creative-agent contracts (ContractRegistry, AssetManifest, RunRecord, tool envelopes). For agent builders, third-party integrations, and

frenum

Deterministic, config-driven guardrails for LLM agent tool calls

@cloudflare/voice

Voice pipeline for Cloudflare Agents — STT, TTS, VAD, streaming, and SFU utilities

request-filtering-agent

An http(s).Agent implementation that block request Private IP address.

@statelyai/agent

Stateful agents that make decisions based on finite-state machine models

@llamaflowjs/autotool

auto transpile your JS function to LLM Agent compatible

@lobehub/icons

Popular AI / LLM Model Brand SVG Logo and Icon Collection

@elyracode/coding-agent

Coding agent CLI with read, bash, edit, write tools and session management

@ruvector/ruvllm

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

@databricks/ai-sdk-provider

Databricks provider for Vercel AI SDK

@self-evolving-harness/kivo

KIVO — Agent 知识平台,覆盖知识提取、存储、检索、迭代、调研、图谱、工作台全生命周期

opencode-plugin-openspec

An OpenCode plugin that integrates OpenSpec, providing a dedicated agent for planning and specifying software architecture.

@playwright/cli

Playwright CLI

@langwatch/server

Run LangWatch locally with one command — `npx @langwatch/server`. Complete LangWatch stack: observability, evaluations, AI gateway, agent simulations.

@rozenite/agent-bridge

React hook API for registering agent tools in React Native

@thirdfy/agent-cli

Thirdfy Agent CLI for onboarding, governance preflight, execute-intent, and status polling.

@wix-pilot/detox

Detox driver for Wix Pilot usage

@hyperspaceng/neural-agent-core

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

llm-polyglot

A universal LLM client - provides adapters for various LLM providers to adhere to a universal interface - the openai sdk - allows you to use providers like anthropic using the same openai interface and transforms the responses in the same way - this allow

agent-booster

Ultra-fast code editing engine - 52x faster than Morph LLM at $0 cost

@agent-score/pay

CLI wallet for one-shell-command agent payments across x402 (Base) and MPP (Tempo, Solana)

infinity-agent

Creates HTTP/HTTPS Agent with Infinity maxSockets

@typia/utils

Superfast runtime validators with only one line

@dudko.dev/agent

Tool-using planning agent over MCP servers, built on the Vercel AI SDK.

agent-hub-llm-sdk

Generic LLM provider SDK with local tool execution for OpenAI-compatible APIs

@nordsym/apiclaw

The Control Plane for AI Agents. 26,701 discoverable APIs, 2,906 callable, 49 fully managed. Agent-native auth: `apiclaw auth login` opens your browser, one-tap sign-in, writes ~/.apiclaw.toml. Four doors: local MCP, CLI, HTTP gateway, Remote MCP. One aut

@lythos/test-utils

![Coverage](https://img.shields.io/badge/coverage-94%25-brightgreen) ![CI](https://img.shields.io/badge/CI-78%20unit%20tests-brightgreen) ![Intent/Plan](https://img.shields.io/badge/arch-intent%2Fplan%2Fexecute-8A2BE2) ![LLM Audit](https://img.shields.io/

agent-device

Agent-native CLI for AI app automation across iOS, Android, tvOS, Android TV, macOS, Linux, and web.

@virtuals-protocol/acp-node-v2

The Agent Commerce Protocol (ACP) Node SDK v2 is a ground-up rewrite of the ACP Node SDK. It replaces the callback/phase-based model with an event-driven architecture built around `AcpAgent` and `JobSession`, with first-class LLM tool integration, pluggab

@xdsjs/llm-wiki-invest

Agent-native LLM Wiki Invest — AI-maintained knowledge base with Obsidian compatibility

@aws-cdk/asset-node-proxy-agent-v6

<!--BEGIN STABILITY BANNER-->

@mondaydotcomorg/atp-vercel-sdk

Vercel AI SDK integration for Agent Tool Protocol.

@typia/interface

Superfast runtime validators with only one line

@novaqore/atom

Atom is a full-system code agent with root-level access, built for isolated servers.

@goyamegh/agent-health

Agent Evaluation and Observability Framework

@cool-ai/beach-protocol

Envelope shape, canonical part-type registry, and Agent Card for Beach applications.

user-agent-data-types

Type definition for navigator.userAgentData

agent-inspect

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP

dance-of-tal

Dance of Tal — Agent Manager for Agentic AI. CLI for managing AI agent personas, rules, and workflows.

@egjs/agent

Extracts browser and operating system information from the user agent string or user agent object(userAgentData).

recursive-llm-ts

TypeScript bridge for recursive-llm: Recursive Language Models for unbounded context processing with structured outputs

opencode-claude-auth

OpenCode plugin that uses your Claude Code credentials — no separate login needed.

@vscode/proxy-agent

NodeJS http(s) agent implementation for VS Code

@toon-format/toon

Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware encoding of JSON for LLM prompts

@grafana/llm

A library for working with LLMs in Grafana plugins

@mondaydotcomorg/atp-runtime

Runtime SDK injected into sandbox for Agent Tool Protocol

ccqa

Browser test recorder powered by Claude Code and agent-browser

llmz

LLMz - An LLM-native Typescript VM built on top of Zui

@amodalai/core

Amodal agent runtime core

@lmstudio/sdk

LM Studio SDK

ua-is-frozen

A freeze-test for your user-agent string

@llm-ui/code

[llm-ui](https://llm-ui.com) code block.

balchemy

Scaffold and run a local Balchemy MCP agent client

@hyperbrowser/agent

Hyperbrowsers Web Agent

@foxxytux/buddy-agent-core

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

aiyu-multi-agent

AI Agent Platform — 84 Agents, 46 Skills, 78 Workflows, 14 Tools, 5 LLM Providers (OpenAI/Claude/Groq/Ollama/Mock), Smart Init, Frontmatter Task Runner, Plugin System, Agent Testing, Publishing

llm-agent-cli

Terminal AI agent powered by LLM-Router — read files, run commands, edit code, git integration, security scanning

@openrouter/sdk

The OpenRouter TypeScript SDK is a type-safe toolkit for building AI applications with access to 400+ language models through a unified API.

@kolisachint/hoocode-agent-core

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

agent-install

Install SKILL.md files, MCP servers, and AGENTS.md guidance for any coding agent. Ships both a Node API and a CLI.

deepagents

Deep Agents - a library for building controllable AI agents with LangGraph

@posthog/pi

PostHog LLM Analytics extension for pi coding agent

cli-contracts

Contract-first specification and toolchain for command line interfaces

Browse other source pages