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 57 of 80
Exotic AI mechanisms for emergent behavior - Neural Autonomous Orgs, Morphogenetic Networks, Time Crystals
Local-first context rails for AI coding agents: reversible terminal compression, progressive repo reading, SDD workflows, hooks, benchmarks, memory and cache-friendly payloads.
Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw
Ready-made React UI components for the Akropolys intent platform.
SDK for obtaining scoped tokens for third-party services on behalf of apps or users. Authenticates the calling Vercel project via [`@vercel/oidc`](https://www.npmjs.com/package/@vercel/oidc) and exchanges the OIDC token for a Vercel Connect-issued credent
CLI tools for vellum-assistant
Built-in agent adapters for adapters
Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.
Type-safe macOS iMessage SDK for TypeScript
Core reasoning and planning engine for Bandit Agent Framework.
Provider integration adapters for Bandit Agent Framework.
Node.js adapter for the Bandit Agent Framework.
UI primitives for the Bandit Agent Framework.
GitHub Actions adapter for the Bandit Agent Framework.
Tailored AI CLI — lightweight, modular AI agent framework optimized for local LLMs. `tai` command.
Agent core library: runtime, config, tools, providers, channels, db, cron, hooks. Lightweight, modular AI agent framework optimized for local LLMs.
Agentic AI Shadowing — observes tasks, generates SOPs, fully local and anonymized
Optional autonomous multi-session orchestrator CLI for agentic-workflow-kit.
MCP server (stdio) exposing survey tools over core, plus the agentic-survey CLI.
Process transparency for agentic work.
KOB CLI v2 - a beautiful, fully agentic AI coding assistant for your terminal. Made in Thailand.
Embeddable agentic chat widget powered by Anthropic
Native Incorpus CLI installer for agentic business workflows
Done Agent Pack CLI — turn any folder into a Done-style agentic workspace for Claude Code, Cursor, Codex, Antigravity
One-command installer for OmegaOS — the agentic terminal OS (rmux + AI orchestration). Run: npx omega-os
Agentic persistent planning
A strict, opinionated linter for agentic manifesto files (SKILL.md, CLAUDE.md, AGENTS.md)
Agentic AI library for automated company research
LangGraph-powered intelligence orchestration for Tuff (providers, prompts, quotas, audit)
Pull requests for AI memory.
Scaffold a Slack-native AI agent in one command.
Typed client for 2s — the (most) everything API. Pay-per-call AI-agent data APIs, settled in USDC on Base or Solana via x402.
Run manual test cases with an AI agent in a real browser
MCP server that spawns isolated LLM agent sessions across multiple providers
Record/replay LLM & agent API calls for fast, free, deterministic tests. In-process recorder + optional gateway shim.
Deterministic skill-rails backend (knowledge/context reads, search, self-review gating, Ed25519 audit chain, Pocket Watch drift) for the MaintainabilityAI agentic-SDLC Copilot agents
General-purpose agent with transport abstraction, state management, and attachment support
Stealth Chromium that passes every bot detection test. Drop-in Playwright/Puppeteer replacement with source-level fingerprint patches.
Coding agent CLI with read, bash, edit, write tools and session management
Agent SDK: interfaces + createAgent() + generate loop. One package.
CLI installer for the Hookstack catalogue of Claude Code hooks
Automatic multi-account failover & rotation for Pi Agent across Anthropic (Claude), OpenAI/ChatGPT Codex, Qwen/Alibaba, and Ollama. Auto-discovers authenticated accounts, grows the rotation on login, and drops accounts on logout, expiry, or quota/rate-lim
Speaker plugin for opencode — speaks agent events through pluggable TTS providers.
The CRM your AI agents actually run — local-first, MCP-native, one autonomous agent per customer. 111 MCP tools for Claude Code, Codex & Cursor.
Abkus Code — autonomous development agent. Like Claude Code but open-source.
Terminal-first relay for paired AI coding agents (Claude + Codex), driven by structured workflows.
Multi-agent AI engineering runtime + RAG Confidence Layer (PIL over MCP for Cursor, Claude Code, Codex, OpenCode)
Local AI control plane with a resident private assistant for task execution and a unified model proxy API for Claude Code, Codex CLI, Gemini CLI, OpenClaw, accounts, API keys, logs, and usage.
Local Markdown knowledge base for AI assistants. Save what your AI reads, ask it later, and keep everything local.
POMASA Multi-Agent System Dashboard
Foundation core for the iapeer multi-agent ecosystem: identity, registry, storage, codec.
Standalone npm launcher for Canvas Flow multi-agent GenAI workflows.
Multi-agent workflow orchestration for Pi — stateful workflow management with persistence, state machine, and execution tracing.
AI-native development companion — Agent, Ask, Plan, Auto, and Multi-Agent modes in your terminal.
Production-grade CLI multi-agent AI assistant, real-time voice controller, and automated background job scheduler for local and cloud environments.
Multi-agent project orchestrator for hydra-acp — decomposes a goal into a task DAG, spawns worker sessions, coordinates via prompts.
Swarm DAO governance adapter for OpenCode — multi-agent deliberation, quality gates, and structured decision-making
OpenCode add-on providing structured multi-agent workflows, durable task artifacts, and an orchestrator agent for complex AI coding sessions.
Multi-agent local code review powered by the Vercel AI SDK
Swarm DAO adapter for the Pi coding agent — multi-agent governance tools, commands, and event hooks
Multi-agent AI collaboration platform for end-to-end software delivery
Reference implementation of the Ironclad standard — multi-agent dev harness for Claude Code.
Open-source coding-agent CLI. Terminal-first, multi-agent, self-improving. Supports OpenAI, Anthropic, Gemini, Ollama, and 13 more providers.
oh-my-deepseek (omd) — Multi-agent orchestration layer for DeepSeek with prompt caching optimization.
Multi-agent orchestration layer for Kimi Code CLI
Multi-agent team orchestration on top of hoocode agents: DAG dispatch, planner, agent registry, tagged event channel
Doctrina CLI — spec-driven, AGENTS.md-native framework for multi-agent AI development.
Core agent framework — base class, lifecycle, handlers, config loader
VS Code adapter for the Bandit Agent Framework.
Web adapter for the Bandit Agent Framework.
A minimal Node.js coding agent framework
TypeScript agent framework with tools, memory, and multi-agent orchestration.
Cross-platform CLI for the agentic ticket pipeline (dev-* + plan-* commands).
Bundler-agnostic Agentic React runtime selection and MCP primitives
Scaffold a new agentic AI application with Next.js, Better Auth, and AI SDK
Vite adapter for Agentic React local dev integration
Native LoopPause human-in-the-loop nodes for LangGraph (TypeScript)
Cairn — an AI that walks your system and leaves a trail of tests. Autonomous QA agent (UI today; API/unit/docs planned) on LangGraph + Claude/OpenRouter, with self-improvement via Langfuse.
MCP server that lets AI agents manage an Oryntra workspace (agents, specialists, LLM keys, products, knowledge base, external tools) via a workspace-scoped API token.
TypeScript SDK for AgentState — conversation history for AI agents
AI-Powered DevOps Deployment Agent
openHermit: Loop Engineering workbench for local AI agent runtimes.
Reusable AI agent skills, project playbook templates, and a small operator-controlled runtime harness.
AI-Agent CLI tool named oy
A lightweight framework for multi-AI-agent cohabitation — where AI agents live together, share memory, and collaborate like roommates. 🏠🤖
MCP server for agentbank — let your AI agent discover Curless merchants and pay them.
CLI tool for searching, installing, and managing AI agent skills
AI agent skills and subagents for Polygraph sessions, repository context, and coordination
ClankerOverflow CLI for logging and searching AI agent solutions
A repo-aware package manager for AI-agent skills, rules, and instructions
A hackable, hexagonal-architecture LLM agent harness for the terminal — connects to Ollama, OpenRouter, Gemini, Groq, DeepSeek, or any OpenAI-compatible endpoint
Olbos MCP server — any LLM agent gets a yield treasury on Solana: deploy, fund (the x402 payment IS the deposit), rebalance, withdraw.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Control Philips Hue lights locally via the bridge API. Works with any LLM/agent.
Control TP-Link Kasa smart plugs and switches locally. Works with any LLM/agent.
AI-powered code agent workflows for Loopstack — codebase exploration, analysis, and more
Fractal memory system for OpenCode with semantic search and automatic compression.
Provider-agnostic agent harness — memory, tools, sub-agents, and observability wrapped around any LLM.
Create a new BackendKit agent project