Skip to main content

The Multi-Agent Framework

Project description

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 software entity for complex tasks.

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

Open in Dev Containers Open in GitHub Codespaces Hugging Face

  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-Role Schematic (Gradually Implementing)

News

🚀 Jan 03: Here comes v0.6.0! In this version, we added serialization and deserialization of important objects and enabled breakpoint recovery. We upgraded OpenAI package to v1.6.0 and supported Gemini, ZhipuAI, Ollama, OpenLLM, etc. Moreover, we provided extremely simple examples where you need only 7 lines to implement a general election debate. Check out more details here!

🚀 Dec 15: v0.5.0 is released! We introduced incremental development, facilitating agents to build up larger projects on top of their previous efforts or existing codebase. We also launched a whole collection of important features, including multilingual support (experimental), multiple programming languages support (experimental), incremental development (experimental), CLI support, pip support, enhanced code review, documentation mechanism, and optimized messaging mechanism!

Install

Pip installation

# Step 1: Ensure that Python 3.9+ is installed on your system. You can check this by using:
# You can use conda to initialize a new python env
#     conda create -n metagpt python=3.9
#     conda activate metagpt
python3 --version

# Step 2: Clone the repository to your local machine for latest version, and install it.
git clone https://github.com/geekan/MetaGPT.git
cd MetaGPT
pip3 install -e .     # or pip3 install metagpt  # for stable version

# Step 3: setup your OPENAI_API_KEY, or make sure it existed in the env
mkdir ~/.metagpt
cp config/config.yaml ~/.metagpt/config.yaml
vim ~/.metagpt/config.yaml

# Step 4: run metagpt cli
metagpt "Create a 2048 game in python"

# Step 5 [Optional]: If you want to save the artifacts like diagrams such as quadrant chart, system designs, sequence flow in the workspace, you can execute the step before Step 3. By default, the framework is compatible, and the entire process can be run completely without executing this step.
# If executing, ensure that NPM is installed on your system. Then install mermaid-js. (If you don't have npm in your computer, please go to the Node.js official website to install Node.js https://nodejs.org/ and then you will have npm tool in your computer.)
npm --version
sudo npm install -g @mermaid-js/mermaid-cli

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 config.yaml
docker pull metagpt/metagpt:latest
mkdir -p /opt/metagpt/{config,workspace}
docker run --rm metagpt/metagpt:latest cat /app/metagpt/config/config.yaml > /opt/metagpt/config/key.yaml
vim /opt/metagpt/config/key.yaml # Change the config

# Step 2: Run metagpt demo with container
docker run --rm \
    --privileged \
    -v /opt/metagpt/config/key.yaml:/app/metagpt/config/key.yaml \
    -v /opt/metagpt/workspace:/app/metagpt/workspace \
    metagpt/metagpt:latest \
    metagpt "Write a cli snake game"

detail installation please refer to docker_install

QuickStart & Demo Video

https://github.com/geekan/MetaGPT/assets/34952977/34345016-5d13-489d-b9f9-b82ace413419

Tutorial

Support

Discard Join US

📢 Join Our Discord Channel!

Looking forward to seeing you there! 🎉

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 Jürgen Schmidhuber},
      year={2023},
      eprint={2308.00352},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metagpt-0.6.4.tar.gz (200.0 kB view details)

Uploaded Source

Built Distribution

metagpt-0.6.4-py3-none-any.whl (271.3 kB view details)

Uploaded Python 3

File details

Details for the file metagpt-0.6.4.tar.gz.

File metadata

  • Download URL: metagpt-0.6.4.tar.gz
  • Upload date:
  • Size: 200.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.12.0 pkginfo/1.7.1 requests/2.28.2 requests-toolbelt/0.9.1 tqdm/4.62.0 CPython/3.7.3

File hashes

Hashes for metagpt-0.6.4.tar.gz
Algorithm Hash digest
SHA256 00fe0d6ab2b97a7cdae9678d654363a0e233f2f027d9d8f14b3eb2683b81955e
MD5 80d5a75afbe029bacb6b76c72bf87ff7
BLAKE2b-256 f35eb7b2e7f2058a739224eb665f56900f50aafec759327b621b9b9fe23b24ab

See more details on using hashes here.

File details

Details for the file metagpt-0.6.4-py3-none-any.whl.

File metadata

  • Download URL: metagpt-0.6.4-py3-none-any.whl
  • Upload date:
  • Size: 271.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/4.12.0 pkginfo/1.7.1 requests/2.28.2 requests-toolbelt/0.9.1 tqdm/4.62.0 CPython/3.7.3

File hashes

Hashes for metagpt-0.6.4-py3-none-any.whl
Algorithm Hash digest
SHA256 4705eba9869302f73bcc3991ff12ea25ff849a3ebd5e69052244c1e3562fea01
MD5 005425307e3ab7321426659fb2bd86c3
BLAKE2b-256 7196bb97193a07de268ed41f4fd6acd2636faea9683427015df5e16d9af214ef

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page