MetaGPT

Frameworks & SDKs 💻 Python ⚖️ MIT 🔴 No recent commits
70.2k stars

MetaGPT is a multi-agent framework that assigns different roles to LLMs to form a collaborative software company. It takes a one-line requirement and outputs user stories, requirements, APIs, documents, and code. It is for developers who want to automate complex software development tasks using AI agents.

How To Install MetaGPT - Build A Startup With One Prompt!!

🎬 How To Install MetaGPT - Build A Startup With One Prompt!! · Matthew Berman

✨ Key features

  • Takes one-line requirements and generates full project documentation and code.
  • Simulates a software company with product managers, architects, and engineers.
  • Supports multiple LLM backends including OpenAI, Azure, Ollama, and Groq.
  • Provides CLI and Python library interfaces for easy integration.
  • Includes Data Interpreter role for data analysis and code writing.
  • Orchestrates SOPs to coordinate multi-agent collaboration.

🎯 Use cases

  • Automatically generate a complete software project from a single prompt.
  • Run data analysis tasks with code generation and plotting.
  • Create user stories, competitive analysis, and API designs.
  • Build custom multi-agent systems for complex workflows.

📦 Installation

🧰 Requirements: Python 3.9 to 3.11, Node.js and pnpm installed, and an LLM API key (e.g., OpenAI) configured.

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.

🚀 Usage

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

Or as a 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(" ")
print(repo)  # it will print the repo structure with files

❓ FAQ

What Python versions are supported?

Python 3.9 or later, but less than 3.12, is required.

How do I configure the LLM?

Run metagpt --init-config to create ~/.metagpt/config2.yaml, then edit it with your LLM settings such as api_type, model, base_url, and api_key.

Can I use MetaGPT as a Python library?

Yes, you can import generate_repo from metagpt.software_company and pass a requirement string to generate a project repository.

What is the Data Interpreter?

It is a role in MetaGPT that can run data analysis tasks, as shown in the example that runs analysis on the Iris dataset and includes a plot.

📊 Repository

Stars★ 70,230
Forks🍴 8,925
Open issues🐛 132
Last commit🕒 Jan 21, 2026
Created📅 Jun 2023
Language💻 Python
License⚖️ MIT
Websiteatoms.dev

🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.