/ README.md
README.md
1 2 # MetaGPT: The Multi-Agent Framework 3 4 <p align="center"> 5 <a href=""><img src="docs/resources/MetaGPT-new-log.png" alt="MetaGPT logo: Enable GPT to work in a software company, collaborating to tackle more complex tasks." width="150px"></a> 6 </p> 7 8 <p align="center"> 9 [ <b>En</b> | 10 <a href="docs/README_CN.md">δΈ</a> | 11 <a href="docs/README_FR.md">Fr</a> | 12 <a href="docs/README_JA.md">ζ₯</a> ] 13 <b>Assign different roles to GPTs to form a collaborative entity for complex tasks.</b> 14 </p> 15 16 <p align="center"> 17 <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT"></a> 18 <a href="https://discord.gg/DYn29wFk9z"><img src="https://img.shields.io/badge/Join-Discord-gGnrXvVz7a?logo=discord" alt="Discord Follow"></a> 19 <a href="https://twitter.com/MetaGPT_"><img src="https://img.shields.io/twitter/follow/MetaGPT?style=social" alt="Twitter Follow"></a> 20 </p> 21 22 <h4 align="center"> 23 24 </h4> 25 26 ## News 27 28 π Mar. 10, 2025: π [mgx.dev](https://mgx.dev/) is the #1 Product of the Week on @ProductHunt! π 29 30 π Mar. 4, 2025: π [mgx.dev](https://mgx.dev/) is the #1 Product of the Day on @ProductHunt! π 31 32 π Feb. 19, 2025: Today we are officially launching our natural language programming product: [MGX (MetaGPT X)](https://mgx.dev/) - the world's first AI agent development team. More details on [Twitter](https://x.com/MetaGPT_/status/1892199535130329356). 33 34 π Feb. 17, 2025: We introduced two papers: [SPO](https://arxiv.org/pdf/2502.06855) and [AOT](https://arxiv.org/pdf/2502.12018), check the [code](examples)! 35 36 π Jan. 22, 2025: Our paper [AFlow: Automating Agentic Workflow Generation](https://openreview.net/forum?id=z5uVAKwmjf) accepted for **oral presentation (top 1.8%)** at ICLR 2025, **ranking #2** in the LLM-based Agent category. 37 38 ππ [Earlier news](docs/NEWS.md) 39 40 ## Software Company as Multi-Agent System 41 42 1. MetaGPT takes a **one line requirement** as input and outputs **user stories / competitive analysis / requirements / data structures / APIs / documents, etc.** 43 2. Internally, MetaGPT includes **product managers / architects / project managers / engineers.** It provides the entire process of a **software company along with carefully orchestrated SOPs.** 44 1. `Code = SOP(Team)` is the core philosophy. We materialize SOP and apply it to teams composed of LLMs. 45 46  47 48 <p align="center">Software Company Multi-Agent Schematic (Gradually Implementing)</p> 49 50 ## Get Started 51 52 ### Installation 53 54 > 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`. 55 > You can use conda like this: `conda create -n metagpt python=3.9 && conda activate metagpt` 56 57 ```bash 58 pip install --upgrade metagpt 59 # or `pip install --upgrade git+https://github.com/geekan/MetaGPT.git` 60 # or `git clone https://github.com/geekan/MetaGPT && cd MetaGPT && pip install --upgrade -e .` 61 ``` 62 63 **Install [node](https://nodejs.org/en/download) and [pnpm](https://pnpm.io/installation#using-npm) before actual use.** 64 65 For detailed installation guidance, please refer to [cli_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-stable-version) 66 or [docker_install](https://docs.deepwisdom.ai/main/en/guide/get_started/installation.html#install-with-docker) 67 68 ### Configuration 69 70 You can init the config of MetaGPT by running the following command, or manually create `~/.metagpt/config2.yaml` file: 71 ```bash 72 # Check https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html for more details 73 metagpt --init-config # it will create ~/.metagpt/config2.yaml, just modify it to your needs 74 ``` 75 76 You can configure `~/.metagpt/config2.yaml` according to the [example](https://github.com/geekan/MetaGPT/blob/main/config/config2.example.yaml) and [doc](https://docs.deepwisdom.ai/main/en/guide/get_started/configuration.html): 77 78 ```yaml 79 llm: 80 api_type: "openai" # or azure / ollama / groq etc. Check LLMType for more options 81 model: "gpt-4-turbo" # or gpt-3.5-turbo 82 base_url: "https://api.openai.com/v1" # or forward url / other llm url 83 api_key: "YOUR_API_KEY" 84 ``` 85 86 ### Usage 87 88 After installation, you can use MetaGPT at CLI 89 90 ```bash 91 metagpt "Create a 2048 game" # this will create a repo in ./workspace 92 ``` 93 94 or use it as library 95 96 ```python 97 from metagpt.software_company import generate_repo 98 from metagpt.utils.project_repo import ProjectRepo 99 100 repo: ProjectRepo = generate_repo("Create a 2048 game") # or ProjectRepo("<path>") 101 print(repo) # it will print the repo structure with files 102 ``` 103 104 You can also use [Data Interpreter](https://github.com/geekan/MetaGPT/tree/main/examples/di) to write code: 105 106 ```python 107 import asyncio 108 from metagpt.roles.di.data_interpreter import DataInterpreter 109 110 async def main(): 111 di = DataInterpreter() 112 await di.run("Run data analysis on sklearn Iris dataset, include a plot") 113 114 asyncio.run(main()) # or await main() in a jupyter notebook setting 115 ``` 116 117 118 ### QuickStart & Demo Video 119 - Try it on [MetaGPT Huggingface Space](https://huggingface.co/spaces/deepwisdom/MetaGPT-SoftwareCompany) 120 - [Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!](https://youtu.be/uT75J_KG_aY) 121 - [Official Demo Video](https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d) 122 123 https://github.com/user-attachments/assets/888cb169-78c3-4a42-9d62-9d90ed3928c9 124 125 ## Tutorial 126 127 - π [Online Document](https://docs.deepwisdom.ai/main/en/) 128 - π» [Usage](https://docs.deepwisdom.ai/main/en/guide/get_started/quickstart.html) 129 - π [What can MetaGPT do?](https://docs.deepwisdom.ai/main/en/guide/get_started/introduction.html) 130 - π How to build your own agents? 131 - [MetaGPT Usage & Development Guide | Agent 101](https://docs.deepwisdom.ai/main/en/guide/tutorials/agent_101.html) 132 - [MetaGPT Usage & Development Guide | MultiAgent 101](https://docs.deepwisdom.ai/main/en/guide/tutorials/multi_agent_101.html) 133 - π§βπ» Contribution 134 - [Develop Roadmap](docs/ROADMAP.md) 135 - π Use Cases 136 - [Data Interpreter](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/interpreter/intro.html) 137 - [Debate](https://docs.deepwisdom.ai/main/en/guide/use_cases/multi_agent/debate.html) 138 - [Researcher](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/researcher.html) 139 - [Receipt Assistant](https://docs.deepwisdom.ai/main/en/guide/use_cases/agent/receipt_assistant.html) 140 - β [FAQs](https://docs.deepwisdom.ai/main/en/guide/faq.html) 141 142 ## Support 143 144 ### Discord Join US 145 146 π’ Join Our [Discord Channel](https://discord.gg/ZRHeExS6xv)! Looking forward to seeing you there! π 147 148 ### Contributor form 149 150 π [Fill out the form](https://airtable.com/appInfdG0eJ9J4NNL/pagK3Fh1sGclBvVkV/form) to become a contributor. We are looking forward to your participation! 151 152 ### Contact Information 153 154 If you have any questions or feedback about this project, please feel free to contact us. We highly appreciate your suggestions! 155 156 - **Email:** alexanderwu@deepwisdom.ai 157 - **GitHub Issues:** For more technical inquiries, you can also create a new issue in our [GitHub repository](https://github.com/geekan/metagpt/issues). 158 159 We will respond to all questions within 2-3 business days. 160 161 ## Citation 162 163 To stay updated with the latest research and development, follow [@MetaGPT_](https://twitter.com/MetaGPT_) on Twitter. 164 165 To cite [MetaGPT](https://openreview.net/forum?id=VtmBAGCN7o) in publications, please use the following BibTeX entries. 166 167 ```bibtex 168 @inproceedings{hong2024metagpt, 169 title={Meta{GPT}: Meta Programming for A Multi-Agent Collaborative Framework}, 170 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}, 171 booktitle={The Twelfth International Conference on Learning Representations}, 172 year={2024}, 173 url={https://openreview.net/forum?id=VtmBAGCN7o} 174 } 175 ``` 176 177 For more work, please refer to [Academic Work](docs/ACADEMIC_WORK.md).