# FoundationAgents/MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Repository: https://github.com/FoundationAgents/MetaGPT
Canonical: https://ross.abutalabs.com/products/metagpt
Homepage: https://atoms.dev/
Language: Python
License: MIT
License Family: permissive
Topics: agent, gpt, llm, metagpt, multi-agent
Last push: 2026-01-21T10:12:33+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 63, release rhythm 8, longevity 82
- inputs: {"age_days": 1160, "days_push": 224, "days_rel": 542, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 70050, forks 8907 (observed 2026-08-28T04:12:20.941598+00:00)

## What it is
MetaGPT is an open-source multi-agent framework that assigns roles like product manager, architect, and engineer to LLM-powered agents, simulating a software company's workflow. Given a one-line requirement, it produces artifacts such as user stories, competitive analysis, requirements, data structures, APIs, and code via orchestrated standard operating procedures.

## Use cases
- generate a full software project from a one-line requirement
- orchestrate multiple LLM agents with role-based collaboration
- automatically produce PRDs, API designs, and code from prompts
- build custom multi-agent workflows in Python
- research on agentic workflow generation and LLM collaboration

## When to choose
- you want a mature, well-cited multi-agent framework with an active community
- you need role-based agent teams following SOPs to generate software artifacts
- you are doing research or prototyping with LLM-based agent collaboration in Python

## When to avoid
- you need a single-agent chatbot or simple LLM wrapper
- you require a no-code hosted product rather than a Python framework
- your Python version is outside the supported 3.9-3.11 range

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, workflow-automation
- domain: large-language-models, developer-tools
- platform: python, cross-platform, cli
- tags: multi-agent, llm, sop, software-company-simulation, natural-language-programming, gpt, ai-agents, automation

## Member repositories
- FoundationAgents/MetaGPT (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:20.941598+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:16:23.095341+00:00, confidence not recorded.
  - readme: https://github.com/FoundationAgents/MetaGPT (fetched 2026-08-28T04:12:20.941598+00:00, sha 352757c57b6e)
  - homepage: https://atoms.dev/ (fetched 2026-08-28T17:50:54.607543+00:00, sha 04c6321099bc)
  - site_page: https://atoms.dev/about (fetched 2026-08-28T17:50:54.617594+00:00, sha 655612249838)
  - site_page: https://atoms.dev/pricing (fetched 2026-08-28T17:50:54.619566+00:00, sha 0236aa8148c6)
- Data as of 2026-08-30T08:39:29.467469+00:00.