MetaGPT

Introduce MetaGPT

MetaGPT is a Multi-Agent Framework designed to assign various roles to GPTs (Generative Pre-trained Transformers) to collaborate on complex software tasks. By inputting a one-line requirement, MetaGPT generates user stories, competitive analysis, requirements, data structures, APIs, and other related documents. The framework includes product managers, architects, project managers, and engineers, offering the entire process of a software company with standard operating procedures. It can be installed traditionally or via Docker, and users can specify preferences for the platform or tools they want to use. Additionally, the summary includes instructions on how to use the startup.py script to initiate a software startup and contact information for inquiries.

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.

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

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.