npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

multisync

v1.1.2

Published

Multi-agent workflow orchestrator for AI-powered task automation

Readme

Multisync 🔄

npm version CI Release Status

Multi-agent workflow orchestrator for AI-powered automation
Compose, validate, and run AI agent workflows in Node.js & via CLI.

🌐 Dashboarddashboard.multisync.io
📖 Docsmultisync.io


✨ Features

  • 🔄 Multi-Agent Workflows: Chain AI agents in sequence or review loops
  • 📋 Structured Outputs: Enforce JSON Schema for safe responses
  • 👀 Agent Reviewer: Add QA cycles where agents critique each other
  • 🖥️ CLI & Interactive Mode: Run configs directly from terminal
  • 🔧 MCP Server Integration: Stdio + HTTP support
  • 🛡 System Validation: API key, Node.js, deps checked before run

🚀 Quick Start

Install

# CLI (global)
npm install -g multisync

# Library (inside your project)
npm install multisync

🖥️ CLI Usage

# Run with a config file
multisync --config=my-workflow.json

# Enable verbose logging
multisync --config=my-workflow.json --verbose

# Run system validation
multisync --setup

📦 Library Usage (Node.js Project)

You can import multisync/core into your own project to run agent flows directly:

// myApp.js
import { runFlow, validateConfig } from 'multisync/core';
import fs from 'node:fs/promises';

async function main() {
  const raw = await fs.readFile('./my-workflow.json', 'utf8');
  const config = JSON.parse(raw);

  // Validate before running
  validateConfig(config);

  // Run flow with a user prompt
  const result = await runFlow(config, 'Write a haiku about the ocean');

  console.log('Workflow result:', result);
}

main().catch(console.error);

Example output:

{
  "result": "Whispers on the tide / Echoes drift across the waves / Silence sings ashore"
}

📋 Config Example

{
  "outputSchemas": {
    "ResultString": {
      "type": "object",
      "properties": { "result": { "type": "string" } },
      "required": ["result"]
    }
  },
  "agents": {
    "echo": {
      "name": "Echo Agent",
      "instructions": "Repeat the user input inside the result property",
      "outputSchemaRef": "ResultString"
    }
  },
  "flow": {
    "steps": [{ "id": "step1", "type": "single_agent", "agentRef": "echo" }]
  }
}

🔑 Prerequisites

  • Node.js 18+: Required for ES modules and modern JavaScript features
  • OpenAI API Key: Set as OPENAI_API_KEY system environment variable
  • MCP Servers: If using MCP integration (optional)

💡 Tip: Set your OpenAI API key as a system environment variable:

export OPENAI_API_KEY="your-api-key-here"

📋 CLI Commands

| Command | Description | | ---------------------------------------- | ------------------------------- | | multisync | Start interactive mode | | multisync --config=file.json | Run with configuration file | | multisync --config=file.json --verbose | Run with verbose logging | | multisync --setup | Run system setup and validation | | multisync --help | Show help information |

🛠️ Development

Local Development

# Clone the repository
git clone https://github.com/Multi-Sync/multisync.git
cd multisync

# Install dependencies
npm install

# Run tests
npm test

# Run tests with coverage
npm run test:coverage

# Start development mode
npm run dev

Project Structure

multisync/
├── cli.mjs          # Command-line interface
├── parser.mjs       # Core workflow execution engine
├── validator.mjs    # System validation and checks
├── templates/       # Example configuration files
├── tests/          # Test suite
└── package.json    # Project configuration

🧪 Testing

# Run all tests
npm test

# Run tests in watch mode
npm run test:watch

# Run tests with coverage
npm run test:coverage

# Run specific test file
npm test -- tests/unit/validator.test.mjs

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

🎯 Join our community at multisync.io to see our full vision and roadmap!

🚀 Coming Soon

  • 🦙 Ollama Integration: Run workflows with local AI models for offline and privacy-focused use cases
  • 🌐 Multi-Provider Support: Support for Anthropic, Google, and other AI providers
  • 📊 Workflow Analytics: Monitor and optimize your agent workflows
  • 🔐 Enterprise Features: Role-based access control and team collaboration
  • 📱 Mobile App: iOS and Android apps for workflow management

Stay updated at multisync.io!

Development Setup

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests for new functionality
  5. Ensure all tests pass
  6. Submit a pull request

📄 License

Apache 2.0 © Multisync Inc.

Built with ❤️ on top of OpenAI Agents SDK