AI Compare
​
​
ToolsArticlesServices
Best for
    All tools

    Sales

    AI tools for finding leads, qualifying them, preparing quotes, following up and keeping the CRM up to date.

    Marketing

    AI tools for content, social media, images, video, SEO and campaigns.

    Customer service

    AI tools for answering customer emails, chats and calls, handling requests and escalating the hard cases.

    Operations

    AI tools for running the daily work: workflows, scheduling, projects, purchasing and delivery.

    Finance

    AI tools for invoices, bookkeeping, reconciliation, spreadsheets and financial reporting.

    Management & Admin

    AI tools for owners, managers and office staff: planning, reports, documents, meetings, scheduling and everyday admin.

    HR

    AI tools for hiring, screening candidates, onboarding, training and answering employee questions.

    Legal & Compliance

    AI tools for reviewing contracts, tracking deadlines and preparing compliance work for a qualified person to check.

    IT & Development

    AI tools for developers and IT teams: coding, AI models, agents, infrastructure and integrations.

Find AI tools for your team
AllAssistantsWriting & DocsImagesVideoAudioAI AgentsAutomationCode
← Back to tools

β€’

2023-06-30

MetaGPT logo

MetaGPT

Not rated yet

69.5K GitHub stars

Type:

Framework

Platforms:

Github

Task:

Run AI agentsCollaborate with AI agentsAutomate software developmentBuild AI appsCreate product specifications

Best for:

IT & Development
Visit websiteView on GitHub

Pricing


Pricing information has not been added yet.

Overview

MetaGPT is an open-source multi-agent framework that models software and business workflows as teams of specialized AI roles. A user can provide a high-level requirement and the system assigns different responsibilities to agents that behave like product managers, architects, engineers, and other team members, producing intermediate artifacts and coordinating work through structured processes.

The project is best known for its software-development use cases, where agents can move from requirements toward design, implementation, and related outputs, but its underlying role-based coordination concepts can be applied more broadly. MetaGPT is aimed at developers and researchers exploring multi-agent collaboration, standardized operating procedures, and more structured alternatives to a single autonomous agent. It is particularly useful for experimentation with how multiple LLM-driven roles can divide and coordinate complex tasks.

README

MetaGPT: The Multi-Agent Framework

MetaGPT logo: Enable GPT to work in a software company, collaborating to tackle more complex tasks.

[ En | δΈ­ | Fr | ζ—₯ ] Assign different roles to GPTs to form a collaborative entity for complex tasks.

License: MIT Discord Follow Twitter Follow

News

πŸš€ Mar. 10, 2025: πŸŽ‰ mgx.dev is the #1 Product of the Week on @ProductHunt! πŸ†

πŸš€ Mar. Β  4, 2025: πŸŽ‰ mgx.dev is the #1 Product of the Day on @ProductHunt! πŸ†

πŸš€ Feb. 19, 2025: Today we are officially launching our natural language programming product: MGX (MetaGPT X) - the world's first AI agent development team. More details on Twitter.

πŸš€ Feb. 17, 2025: We introduced two papers: SPO and AOT, check the code!

πŸš€ Jan. 22, 2025: Our paper AFlow: Automating Agentic Workflow Generation accepted for oral presentation (top 1.8%) at ICLR 2025, ranking #2 in the LLM-based Agent category.

πŸ‘‰πŸ‘‰ Earlier news

Software Company as Multi-Agent System

  1. MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.
  2. Internally, MetaGPT includes product managers / architects / project managers / engineers. It provides the entire process of a software company along with carefully orchestrated SOPs.
    1. Code = SOP(Team) is the core philosophy. We materialize SOP and apply it to teams composed of LLMs.

A software company consists of LLM-based roles

Software Company Multi-Agent Schematic (Gradually Implementing)

Get Started

Installation

Ensure that Python 3.9 or later, but less than 3.12, is installed on your system. You can check this by using: python --version.
You can use conda like this: conda create -n metagpt python=3.9 && conda activate metagpt

pip install --upgrade metagpt
# or `pip install --upgrade git+https://github.com/geekan/MetaGPT.git`
# or `git clone https://github.com/geekan/MetaGPT && cd MetaGPT && pip install --upgrade -e .`

Install node and pnpm before actual use.

For detailed installation guidance, please refer to cli_install or docker_install

Configuration

You can init the config of MetaGPT by running the following command, or manually create ~/.metagpt/config2.yaml file:

# Check https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html for more details
metagpt --init-config  # it will create ~/.metagpt/config2.yaml, just modify it to your needs

You can configure ~/.metagpt/config2.yaml according to the example and doc:

llm:
  api_type: "openai"  # or azure / ollama / groq etc. Check LLMType for more options
  model: "gpt-4-turbo"  # or gpt-3.5-turbo
  base_url: "https://api.openai.com/v1"  # or forward url / other llm url
  api_key: "YOUR_API_KEY"

Usage

After installation, you can use MetaGPT at CLI

metagpt "Create a 2048 game"  # this will create a repo in ./workspace

or use it as library

from metagpt.software_company import generate_repo
from metagpt.utils.project_repo import ProjectRepo

repo: ProjectRepo = generate_repo("Create a 2048 game")  # or ProjectRepo("<path>")
print(repo)  # it will print the repo structure with files

You can also use Data Interpreter to write code:

import asyncio
from metagpt.roles.di.data_interpreter import DataInterpreter

async def main():
    di = DataInterpreter()
    await di.run("Run data analysis on sklearn Iris dataset, include a plot")

asyncio.run(main())  # or await main() in a jupyter notebook setting

QuickStart & Demo Video

  • Try it on MetaGPT Huggingface Space
  • Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!
  • Official Demo Video

https://github.com/user-attachments/assets/888cb169-78c3-4a42-9d62-9d90ed3928c9

Tutorial

  • πŸ—’ Online Document
  • πŸ’» Usage
  • πŸ”Ž What can MetaGPT do?
  • πŸ›  How to build your own agents?
    • MetaGPT Usage & Development Guide | Agent 101
    • MetaGPT Usage & Development Guide | MultiAgent 101
  • πŸ§‘β€πŸ’» Contribution
    • Develop Roadmap
  • πŸ”– Use Cases
    • Data Interpreter
    • Debate
    • Researcher
    • Receipt Assistant
  • ❓ FAQs

Support

Discord Join US

πŸ“’ Join Our Discord Channel! Looking forward to seeing you there! πŸŽ‰

Contributor form

πŸ“ Fill out the form to become a contributor. We are looking forward to your participation!

Contact Information

If you have any questions or feedback about this project, please feel free to contact us. We highly appreciate your suggestions!

  • Email: alexanderwu@deepwisdom.ai
  • GitHub Issues: For more technical inquiries, you can also create a new issue in our GitHub repository.

We will respond to all questions within 2-3 business days.

Citation

To stay updated with the latest research and development, follow @MetaGPT_ on Twitter.

To cite MetaGPT in publications, please use the following BibTeX entries.

@inproceedings{hong2024metagpt,
      title={Meta{GPT}: Meta Programming for A Multi-Agent Collaborative Framework},
      author={Sirui Hong and Mingchen Zhuge and Jonathan Chen and Xiawu Zheng and Yuheng Cheng and Jinlin Wang and Ceyao Zhang and Zili Wang and Steven Ka Shing Yau and Zijuan Lin and Liyang Zhou and Chenyu Ran and Lingfeng Xiao and Chenglin Wu and J{\"u}rgen Schmidhuber},
      booktitle={The Twelfth International Conference on Learning Representations},
      year={2024},
      url={https://openreview.net/forum?id=VtmBAGCN7o}
}

For more work, please refer to Academic Work.

Releases

Release information has not been added yet.

Related articles

Guides and news that mention this tool.

Z
M
n8n logo

AI Agents in Zapier vs Make vs n8n: Which Is Best?

Comparison
n8n logo

What Is n8n? The Open-Source Workflow Automation Tool Explained

Get started
G
Z
M

AI Email Labeling in Gmail with OpenAI

Use cases
W
n8n logo

AI WhatsApp Customer Support Agent

Use cases
G
n8n logo
Gemini logo

Build a RAG Chatbot over Your Google Drive Documents

Use cases
T
n8n logo
ChatGPT logo

Build an AI Assistant on Telegram (Voice + Text) with n8n

Use cases
Complete your AI stack

Add a general assistant, research, coding, monitoring, and team productivity to your automations.

ChatGPT logo
ChatGPT
General assistant

General-purpose AI assistant for research, writing, coding, data analysis, image creation, and everyday productivity

View tool
Perplexity logo
Perplexity
Research

AI-powered search and research assistant

View tool
Cursor logo
Cursor
Build integrations

AI coding editor and autonomous software development platform

View tool
Best alternatives

Compare similar tools in the same category.

CodeRabbit logo

CodeRabbit

AI-powered code review assistant for pull requests.

OpenClaw logo

OpenClaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Cursor logo

Cursor

AI coding editor and autonomous software development platform

DeepSeek logo

DeepSeek

AI assistant for reasoning, coding, research, and agent tasks

ECC logo

ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

View all in this category
Help
Pick an answer below
Hi! I can point you to the right tool or guide. What are you looking for?
Browse all articles