/MetaGPT

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

Primary LanguagePythonMIT LicenseMIT

MetaGPT: The Multi-Agent Framework

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

Assign different roles to GPTs to form a collaborative entity for complex tasks.

CN doc EN doc JA doc License: MIT roadmap Discord Follow Twitter Follow

Open in Dev Containers Open in GitHub Codespaces Hugging Face

News

πŸš€ Jan. 16, 2024: Our paper MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework accepted for oral presentation (top 1.2%) at ICLR 2024, ranking #1 in the LLM-based Agent category.

πŸš€ Jan. 03, 2024: v0.6.0 released, new features include serialization, upgraded OpenAI package and supported multiple LLM, provided minimal example for debate etc.

πŸš€ Dec. 15, 2023: v0.5.0 released, introducing some experimental features such as incremental development, multilingual, multiple programming languages, etc.

πŸ”₯ Nov. 08, 2023: MetaGPT is selected into Open100: Top 100 Open Source achievements.

πŸ”₯ Sep. 01, 2023: MetaGPT tops GitHub Trending Monthly for the 17th time in August 2023.

🌟 Jun. 30, 2023: MetaGPT is now open source.

🌟 Apr. 24, 2023: First line of MetaGPT code committed.

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)

Install

Pip installation

Ensure that Python 3.9+ 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 metagpt
metagpt --init-config  # create ~/.metagpt/config2.yaml, modify it to your own config
metagpt "Create a 2048 game"  # this will create a repo in ./workspace

or you can use it as library

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

detail installation please refer to cli_install

Docker installation

Note: In the Windows, you need to replace "/opt/metagpt" with a directory that Docker has permission to create, such as "D:\Users\x\metagpt"

# Step 1: Download metagpt official image and prepare config2.yaml
docker pull metagpt/metagpt:latest
mkdir -p /opt/metagpt/{config,workspace}
docker run --rm metagpt/metagpt:latest cat /app/metagpt/config/config2.yaml > /opt/metagpt/config/config2.yaml
vim /opt/metagpt/config/config2.yaml # Change the config

# Step 2: Run metagpt demo with container
docker run --rm \
    --privileged \
    -v /opt/metagpt/config/config2.yaml:/app/metagpt/config/config2.yaml \
    -v /opt/metagpt/workspace:/app/metagpt/workspace \
    metagpt/metagpt:latest \
    metagpt "Create a 2048 game"

detail installation please refer to docker_install

QuickStart & Demo Video

customized_tasks_by_MetaGPT_v2.mp4

Tutorial

Support

Discard Join US

πŸ“’ Join Our Discord Channel!

Looking forward to seeing you there! πŸŽ‰

Contact Information

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

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

Citation

For now, cite the arXiv paper:

@misc{hong2023metagpt,
      title={MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework}, 
      author={Sirui Hong and Mingchen Zhuge and Jonathan Chen and Xiawu Zheng and Yuheng Cheng and Ceyao Zhang and Jinlin Wang and Zili Wang and Steven Ka Shing Yau and Zijuan Lin and Liyang Zhou and Chenyu Ran and Lingfeng Xiao and Chenglin Wu and JΓΌrgen Schmidhuber},
      year={2023},
      eprint={2308.00352},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}