open-multi-agent
A TypeScript multi-agent orchestration framework that decomposes goals into task DAGs and runs them on any LLM.
- Type
- MCP
- Open source
- Yes
- GitHub Stars
- ★ 6.4k
- Source
- mcp-github
Overview
Open Multi-Agent is a TypeScript-based multi-agent orchestration framework. Users simply describe a goal, and the coordinator breaks it down into a task directed acyclic graph (DAG), which then runs on any language model (e.g., Claude, ChatGPT, Gemini, etc.). The framework supports major model providers and can be easily integrated into Node.js backends. Ideal for developers needing dynamic task assignment and collaboration.
Capabilities
- ▪Decompose goals into task DAGs
- ▪Automatically parallelize independent tasks
- ▪Support multiple language models
- ▪Lightweight core engine
- ▪Flexible task scheduling
Use cases
Setup
npm create oma-app@latest or npm install @open-multi-agent/core
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with Open Multi-Agent?
Create a project and launch a multi-agent DAG using the command `npm create oma-app@latest`.
Which language models are supported?
Supports Claude, ChatGPT, Gemini, DeepSeek, and local models.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.