mcp-server

Open-Multi-Agent: AI Workflow Automation

Name: Open-Multi-Agent: AI Workflow Automation
Author: open-multi-agent

Get dynamic AI agent orchestration for your startup with open-multi-agent, used by founders across various niches, with 6.6k+ GitHub stars.

6,625 stars2,415 forksTypeScriptQuality 8/10Updated 7/20/2026100% free · open source

What it does

Open-multi-agent is a TypeScript framework that allows dynamic AI agent orchestration with dynamic workflows, enabling the coordination of tasks across various large language models (LLMs) like Claude, ChatGPT, Gemini, DeepSeek, or local models

Install / run

npm install @open-multi-agent/core @open-multi-agent/runtime

When to use it

•When you need to integrate multiple AI models into a single workflow
•When your startup requires dynamic task planning and execution using different LLMs
•When you want to run AI tasks on any available LLM, whether local or cloud-based

Quick start

1Clone the open-multi-agent repository from GitHub using the command `git clone https://github.com/open-multi-agent/open-multi-agent.git`
2Navigate into the cloned repository with the command `cd open-multi-agent`
3Install the necessary dependencies with the command `npm install`
4Start the open-multi-agent runtime with the command `npx ts-node runtime/index.ts`
5Create a new task definition in the `tasks` directory to define your workflow

Ready-to-paste prompt

To run a task on the Claude LLM, use the following command: `npx ts-node runtime/index.ts --task my-task --model claude`

Heads up: Make sure to have the correct TypeScript version (14 or higher) installed, as open-multi-agent uses TypeScript features that are not compatible with lower versions

Saves to your device