Orchestrate goal-driven TypeScript agent teams with Open Multi Agent

Turn a user goal into a planned multi-agent task DAG, execute independent tasks in parallel, and trace the run from a TypeScript backend.

Prerequisites

Node.js >= 18, npm, API keys for selected model providers or local model provider, optional MCP servers

Installation

Use the upstream install or setup path that matches your environment:

• npm install @open-multi-agent/core
• git clone https://github.com/open-multi-agent/open-multi-agent && cd open-multi-agent
• npm install
• npx tsx examples/basics/team-collaboration.ts

Requirements and caveats from upstream:

• <img src="https://raw.githubusercontent.com/open-multi-agent/open-multi-agent/main/.github/brand/demo-dashboard-hero.gif" alt="Post-run dashboard replaying a completed team run: task DAG with per-node assignee, status...
• Requires Node.js >= 18.
• | Python stack with mature multi-agent ecosystem | CrewAI |

Basic usage or getting-started notes:

• open-multi-agent is a multi-agent orchestration framework for TypeScript backends. Give it a goal; a coordinator agent decomposes it into a task DAG, parallelizes independents, and synthesizes the result. Three runtim...

• Use it in your project

• bash

• Source: https://github.com/open-multi-agent/open-multi-agent

• Extracted from upstream docs: https://raw.githubusercontent.com/open-multi-agent/open-multi-agent/HEAD/README.md

Documentation

• https://github.com/open-multi-agent/open-multi-agent

Source

• Agent Skill Exchange