# MetaGPT: The Multi-Agent Framework

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

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](docs/resources/software_company_cd.jpeg)

Software Company Multi-Role Schematic (Gradually Implementing)

## Examples (fully generated by GPT-4) For example, if you type `python startup.py "Design a RecSys like Toutiao"`, you would get many outputs, one of them is data & api design ![Jinri Toutiao Recsys Data & API Design](docs/resources/workspace/content_rec_sys/resources/data_api_design.png) It requires around **$0.2** (GPT-4 api's costs) to generate one example with analysis and design, around **$2.0** to a full project. ## Installation ### Traditional Installation ```bash # Step 1: Ensure that NPM is installed on your system. Then install mermaid-js. npm --version sudo npm install -g @mermaid-js/mermaid-cli # Step 2: Ensure that Python 3.9+ is installed on your system. You can check this by using: python --version # Step 3: Clone the repository to your local machine, and install it. git clone https://github.com/geekan/metagpt cd metagpt python setup.py install ``` **Note:** - If already have Chrome, Chromium, or MS Edge installed, you can skip downloading Chromium by setting the environment variable `PUPPETEER_SKIP_CHROMIUM_DOWNLOAD` to `true`. - Some people are [having issues](https://github.com/mermaidjs/mermaid.cli/issues/15) installing this tool globally. Installing it locally is an alternative solution, ```bash npm install @mermaid-js/mermaid-cli ``` - don't forget to the configuration for mmdc in config.yml ```yml PUPPETEER_CONFIG: "./puppeteer-config.json" MMDC: "./node_modules/.bin/mmdc" ``` ### Installation by Docker ```bash # Step 1: Download metagpt official image and prepare config.yaml docker pull metagpt/metagpt:v0.3 mkdir -p /opt/metagpt/{config,workspace} docker run --rm metagpt/metagpt:v0.3 cat /app/metagpt/config/config.yaml > /opt/metagpt/config/config.yaml vim /opt/metagpt/config/config.yaml # Change the config # Step 2: Run metagpt demo with container docker run --rm \ --privileged \ -v /opt/metagpt/config:/app/metagpt/config \ -v /opt/metagpt/workspace:/app/metagpt/workspace \ metagpt/metagpt:v0.3 \ python startup.py "Write a cli snake game" # You can also start a container and execute commands in it docker run --name metagpt -d \ --privileged \ -v /opt/metagpt/config:/app/metagpt/config \ -v /opt/metagpt/workspace:/app/metagpt/workspace \ metagpt/metagpt:v0.3 docker exec -it metagpt /bin/bash $ python startup.py "Write a cli snake game" ``` The command `docker run ...` do the following things: - Run in privileged mode to have permission to run the browser - Map host directory `/opt/metagpt/config` to container directory `/app/metagpt/config` - Map host directory `/opt/metagpt/workspace` to container directory `/app/metagpt/workspace` - Execute the demo command `python startup.py "Write a cli snake game"` ### Build image by yourself ```bash # You can also build metagpt image by yourself. git clone https://github.com/geekan/MetaGPT.git cd MetaGPT && docker build -t metagpt:v0.3 . ``` ## Configuration - Configure your `OPENAI_API_KEY` in any of `config/key.yaml / config/config.yaml / env` - Priority order: `config/key.yaml > config/config.yaml > env` ```bash # Copy the configuration file and make the necessary modifications. cp config/config.yaml config/key.yaml ``` | Variable Name | config/key.yaml | env | | ------------------------------------------ | ----------------------------------------- | ----------------------------------------------- | | OPENAI_API_KEY # Replace with your own key | OPENAI_API_KEY: "sk-..." | export OPENAI_API_KEY="sk-..." | | OPENAI_API_BASE # Optional | OPENAI_API_BASE: "https:///v1" | export OPENAI_API_BASE="https:///v1" | ## Tutorial: Initiating a startup ```shell python startup.py "Write a cli snake game" # Use code review will cost more money, but will opt for better code quality. python startup.py "Write a cli snake game" --code_review True ``` After running the script, you can find your new project in the `workspace/` directory. ### Preference of Platform or Tool As the project becomes more complete, the cost of generating the outputs will also gradually increase. Therefore, it is recommended to explicitly specify the platform or tools you want to use when describing the requirements. ```shell python startup.py "Write a cli snake game that runs on Windows" ``` ### Usage ``` NAME startup.py - We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities. SYNOPSIS startup.py IDEA DESCRIPTION We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities. POSITIONAL ARGUMENTS IDEA Type: str Your innovative idea, such as "Creating a snake game." FLAGS --investment=INVESTMENT Type: float Default: 3.0 As an investor, you have the opportunity to contribute a certain dollar amount to this AI company. --n_round=N_ROUND Type: int Default: 5 NOTES You can also use flags syntax for POSITIONAL ARGUMENTS ``` ### Code walkthrough ```python from metagpt.software_company import SoftwareCompany from metagpt.roles import ProjectManager, ProductManager, Architect, Engineer async def startup(idea: str, investment: float = 3.0, n_round: int = 5): """Run a startup. Be a boss.""" company = SoftwareCompany() company.hire([ProductManager(), Architect(), ProjectManager(), Engineer()]) company.invest(investment) company.start_project(idea) await company.run(n_round=n_round) ``` You can check `examples` for more details on single role (with knowledge base) and LLM only examples. ## 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@fuzhi.ai - **GitHub Issues:** For more technical inquiries, you can also create a new issue in our [GitHub repository](https://github.com/geekan/metagpt/issues). We will respond to all questions within 2-3 business days. ## Demo https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d