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 59 of 80
Raindrop observability plugin for OpenCode — automatic session/event/span tracing
Workspace helpers and agent-docs utilities for MetaObjects projects.
[](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2FAgoraIO-Conversational-AI%2Fagent-server-sd
TypeScript SDK and CLI for Tangle Router, Sandbox, model routing, and agent service calls
An embeddable AI-powered customer engagement and interactive product walkthrough SDK. With SalesGenie, you can dynamically guide users through your application using virtual pointers, page highlighting, voice/audio interfaces, and an AI chat assistant.
React/Next.js library for Revrag AI assistant widget
Compress LLM context. Save tokens. Fit more into every request.
Knowledge graph subsystem for Grackle (Neo4j + vector search)
TypeScript client library for connecting to Civic Hub and exposing MCP tools to AI SDKs
Multi-agent orchestration system for Claude Code - Inspired by oh-my-opencode
Universal collaboration protocol + CLI for multi-agent LLM teams
Multi-agent collaboration template for OpenCode
Tako CLI — unified launcher for AI coding tools (Claude Code, Codex, Gemini) with multi-agent session management
A customisable multi-agent workflow-orchestration engine for the pi coding agent.
A configurable, gated, cross-reviewed multi-agent code pipeline: write, gate, review, fix, stop.
Synapse Protocol SDK - Multi-agent systems on NATS with streaming, HTTP bridges, cryptographic ACL, and reputation scoring
Lightweight multi-agent TUI and stable cross-provider collaboration layer for Codex, Claude, Gemini, Grok, Kimi, DeepSeek, and other CLI agents.
Deterministic multi-agent workflows for OpenCode — script agent/pipeline/parallel/phase with journaled replay, plus a native /workflows-style TUI viewer.
Inlay — multi-agent collaboration pipeline for ADR + Context (conflict-free, local-first)
A harness for precise, auditable agent workflows — compose a graph of roles, drive the CLI agents already on your machine, with typed, gated, replayable handoffs. Built on LangGraph.
A layered, provider-agnostic TypeScript library for building agentic bots on Bun & Node.js — tools, skills, memory, MCP & multi-agent.
Multi-agent decision-making framework with flat inference and a 4-layer creative pipeline
Multi-agent development orchestrator with TUI
Multi-agent orchestration system for AI-native software development. Delivers AI-DLC, Agile, and custom SDLC flows as markdown-based agent systems.
Roy — TypeScript LLM chat library core. Multi-provider, rolling compaction, multi-agent, plan mode.
Multi-agent orchestration for VR-based drug discovery using Narupa integration with HoloScript
Framework-agnostic TypeScript SDK client for WAMA (WhatsApp Multi-Agent) enabling token-based message dispatch, media file rendering, and client interactions.
Multi-agent orchestrator for autonomous software development
Ontology-first, local-first agent framework — actions are first-class, governed by domain-object state.
Agent framework — `createAgent` factory, context builder, frontmatter fast-path, and LLM extract pipeline.
Agentic Architecture as Code (AAAC) — installable Cursor agent framework
A2A-compatible Agent framework built on Claude Code SDK
Embeddable web component + headless JS SDK for the clankstack agent framework — paste a snippet and get a streaming agent chat on any website.
Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo
Agentic coding CLI — your terminal AI pair programmer
Telaro LLM-framework adapters bundle. Wrap autogen, crewai, eliza, langchain, llamaindex, or openai-agents runtimes so every tx-emitting action auto-records on Telaro. One install, one import per framework.
JavaScript-native multi-agent orchestration CLI for your terminal. Plan, debate, and run a swarm of agents locally.
Function-call descriptors for Microsoft AutoGen agents to query Telaro trust scores. Drop-in shim that emits the JSON-Schema function specs AutoGen expects.
AI agent framework
Nightly GitHub/Forgejo issue orchestrator — autonomous AI agent coding tool
Jupyter-Native AI Agent Engine
Self-hosted AI agent interaction platform with native agentd service integration.
Local token usage collector for multi-device AI agent accounting.
Multi-provider AI agent CLI supporting Ollama, Bedrock, OpenRouter, OpenAI, Meta, Gemini, xAI, Cloudflare, and Anthropic
Import existing test plans into test-lab.ai from the command line (or an AI agent).
Audit repositories for AI agent readiness
Bridge Feishu/Lark to any ACP-compatible AI agent
Claude Code Web — Replit/Lovable-style chat-first browser UI that wraps the AI agent already installed on your machine.
omnibot CLI and local daemon for real-browser AI agent automation
TypeScript SDK for AgentPact — the AI agent marketplace
Alpha Harness config CLI for validating, initializing, previewing, and activating AI agent configuration.
AI QA Workflow Template — transforms any AI agent into an autonomous QA engineer. AI explores, plans, generates tests, and heals. Scripts execute and report.
NexAgent — locally-runnable AI agent CLI with file editing, tools, and beautiful TUI
Browser-based remote workbench integrating terminal access, file management, and AI agent communication
A pure frontend UI framework for building editors, with built-in AI Agent capabilities.
Free MCP security scanner — finds risks in your AI agent setup
Cross-project LLM agent runtime for Dragonflow — loads agent rows from a per-project `agents` Supabase table and invokes Anthropic / Google / OpenAI models against the v0.1+ invocation contract.
Orchestrator Agent Node for n8n — intelligent multi-output classifier with LLM routing
LLM agent harness for fullstack (NestJS + React) monorepos — guides (skills, instructions) + sensors (dual-tier review agents). Installs into .ruler/ via a 3-way-merge-aware CLI.
General-purpose agent with transport abstraction, state management, and attachment support
General-purpose agent with transport abstraction, state management, and attachment support
CLI that reviews AI coding harness tool calls (Claude Code, OpenCode) before execution via hooks
<!-- generated by scripts/generate-docs.mjs; edit docs/surface.json and docs/packages/llm-transport-effect-ai.md -->
General-purpose agent with transport abstraction, state management, and attachment support
Adds support for LLM locally runned for Capacitor
E2E parity validator for site migrations. Compares prod vs cand and reports UI, functional, SEO, visual, and Web Vitals deltas with an LLM-ranked HTML report.
MCP-native memory server with built-in governance for AI agents
TypeScript SDK for LangSmith Managed Deep Agents.
LangChain.js integration for PostgreSQL pgvector
Neo4j integrations for LangChain.js
A Unified Virtual Filesystem For AI Agents
AI Support Agent CLI client
High-level project management CLI, MCP server, SDK, and AI SDK agent loop for coding agents
Opincer channel plugin for OpenClaw
Deterministic contract layer between humans and coding agents. Drop into any repo to make AI agents (Claude, Codex, Copilot, etc.) operate under explicit, enforceable rules.
Claudin — Claude Code opened to any LLM (OpenAI, Gemini, DeepSeek, Ollama, and 200+ models)
WTT-native connector daemon for Codex, Claude Code, Cursor, Gemini, ACP, and other coding agent surfaces.
Orchestrate 49 AI specialist personalities as a coordinated legion — project initialization, phase planning, parallel execution, quality review, code polish, shipping, and portfolio management.
Vigil — a defensive-cyber terminal agent for Computer Network Defense. Asset discovery, vulnerability assessment, hardening, detection engineering, threat hunting, incident response — on the infrastructure you defend.
Curated skill pack — 20 skills imported from ECC (github.com/affaan-m/ECC). Agent architecture, autonomous loops, testing patterns, DevOps patterns.
A headless, multi-provider AI agent harness. One install gives you the `cortex` CLI and HTTP server: npm i -g nexus-cortex.
Autonomous quality-assurance methodology — agent skills, harness hooks, return-shape schemas, and post-install plumbing that drive the @civitas-cerebrum/element-interactions framework end-to-end.
Autonomous MCP server for Omniology — real-USDC AI agent skill contests on Solana mainnet. A live benchmark against real agents, every 88 seconds, 24/7.
Asana adapter for the @llodev/pm-tasks-* family. Use when the user mentions Asana (create Asana task, publish to Asana, post to Asana, add comment in Asana, --publish-asana, close task, check subtask) or wants to publish a plan as Asana tasks with subtask
Manage sandboxed AI coding agents
Autonomous macOS Computer-Use Desktop Agent powered by Gemini 2.5
Autonomous AI coding agent with knowledge graph memory, DAG swarm orchestration, deployment pipelines, service health monitoring, and adaptive resource management
Codebase indexing and semantic search package for Crayon Terminal AI assistant.
AI building blocks and assistant integration for Praxis UI applications.
Chat SDK — universal TypeScript toolkit for building multi-platform chat bots and AI agents on Slack, Teams, Google Chat, Discord, WhatsApp, and more
Embeddable CareCompass SDK and CLI for healthcare ecosystem integrations with Nexalink onboarding, BAA coverage, and API keys.
AI-powered development assistant for modern software engineering
Babysitter orchestration plugin for OpenCode with SDK-managed process-library bootstrapping and in-turn iteration model
The **[Claude Platform on AWS provider](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic-aws)** for the [AI SDK](https://ai-sdk.dev/docs) gives you access to the Anthropic Messages API hosted in AWS at `aws-external-anthropic.{region}.api.aws`, aut
TypeScript SDK for programmatic access to qwen-code CLI
TomTom Maps for JavaScript
Instance AI is the agent runtime behind the AI assistant experience in n8n. It lets users ask for help with workflows, executions, credentials, nodes, and workflow building from inside an n8n instance.
Vessels CLI — manage your agent communication layer from the terminal
Professional multi-agent codebase auditing and automated repair engine