# MetaGPT

> Multi-agent framework that models a software company.

MetaGPT has a SharkScore of 57.7/100, ranked #248 of 673 in Frameworks & SDKs (updated 2026-11-19).

- Website: https://github.com/FoundationAgents/MetaGPT (github.com)
- Kind: Tool · Pricing: Open source
- Maker: DeepWisdom
- Repository: https://github.com/FoundationAgents/MetaGPT
- Categories: Frameworks & SDKs, Coding
- Verified by the maker: no

## Why it scores 57.7

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 53 | 30% |
| User reviews | no data | 25% |
| Maintenance | 52 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Frameworks & SDKs.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | — |
| GitHub stars | 71.4K |
| Stars, last 90 days | — |
| Downloads, 30 days | 2.9K |
| Reviews | none yet |
| Last update | 301 days ago |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / yes / yes / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, MetaGPT is an open-source multi-agent framework for software tasks; its latest measured release was v0.8.1 on 2024-04-22. [E1; MEASURED]

MetaGPT is a framework that assigns different roles to LLMs and coordinates them through software-development procedures. It can generate project artifacts and code, and can be used from a CLI or as a Python library. The repository lists an MIT license. [E1]

### Pros

- Supports both CLI use and a Python library workflow. [E1]
- Documents a range of software-planning outputs as well as repository generation. [E1]
- The repository lists an MIT license. [E1]

### Cons

- The documented setup requires Python 3.9 or later but below 3.12, and says to install Node and pnpm before use. [E1]
- The example configuration requires an API key and has users configure an LLM provider and model. [E1]
- No public prices found on the pages we checked.
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
- No release in the last 180 days (latest: v0.8.1 on 2024-04-22).

### Pricing

No public prices found on the pages we checked (2026-11-18).

### Sources

- https://github.com/FoundationAgents/MetaGPT (fetched 2026-11-18)
- https://github.com/pricing (fetched 2026-11-18)
- https://docs.github.com/en (fetched 2026-11-18)
- https://docs.github.com/en/site-policy/privacy-policies/github-general-privacy-statement (fetched 2026-11-18)
- https://docs.github.com/en/site-policy/github-terms/github-terms-of-service (fetched 2026-11-18)
- https://github.com/security/advanced-security/code-security (fetched 2026-11-18)

## Top alternatives

1. [Model Context Protocol](https://rankshark.pro/tools/model-context-protocol) — SharkScore 81.7. Open protocol and SDKs that connect AI apps to tools and data.
2. [AI SDK](https://rankshark.pro/tools/ai-sdk) — SharkScore 77.7. TypeScript toolkit for building AI apps and agents.
3. [LangChain](https://rankshark.pro/tools/langchain) — SharkScore 77.7. Build agents and LLM apps in Python and TypeScript.
4. [LangSmith](https://rankshark.pro/tools/langsmith) — SharkScore 76.9. Tracing, evaluation and monitoring for LLM apps.
5. [Transformers](https://rankshark.pro/tools/transformers) — SharkScore 76.9. Hugging Face's library of pretrained models for text, vision and audio.

---
Source: https://rankshark.pro/tools/metagpt · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
