Skip to main content
ME

Multi-agent framework for turning specs into software outputs

MetaGPT assigns different roles to LLMs to simulate a software team. It can turn a short requirement into artifacts like user stories, requirements, APIs, and code repositories.

Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric →

See pricing ↓

Open Source
Chrome Extension
Code Execution
File Access
Multi-Agent
B2B
For Developers
For Teams
Visit MetaGPT

Is this your tool? Claim this listing to manage your content and analytics.

Recent activity

What's happened with MetaGPT lately

  • Score change
    Rubric upgrade v3_0 → v3.1: score 8/32 → 12/36812/36(+4)

    Rubric upgrade: agenticness v3.0 (8 dims, /32) → v3.1 (9 dims, /36). Adds Dim 9 (Operator Sovereignty), splits Dim 6 into 6a/6b lenses, tightens Dim 4 autonomous-retry distinction. Not a product change — score shift reflects new dimension + recalibrated rubric, not a change in the tool. Fanout suppressed.

    See the news that prompted this

News mentions sourced from our news feed; score changes from periodic re-evaluations.

Ask about MetaGPT

Get answers based on MetaGPT's actual documentation

Try asking:

About

What It Is

MetaGPT is an open-source multi-agent framework for building software-oriented AI workflows. According to its README, it organizes LLMs into roles such as product manager, architect, project manager, and engineer so they can work together on complex tasks using defined SOPs.

What to Know

MetaGPT is more of a framework than a finished end-user app. It looks strongest for developers who want to experiment with multi-agent orchestration, code generation, and structured task decomposition. The documentation shows it can generate a repo...

Key Features
Assigns LLMs to software-team roles such as product manager, architect, PM, and engineer
Generates software artifacts from a one-line requirement
Creates a project repository structure from a prompt
Runs from the command line via the `metagpt` CLI
Can be used as a Python library
Use Cases
Generating a starter codebase from a natural-language product requirement
Prototyping multi-agent software workflows for research or internal tools
Running scripted data-analysis tasks through the Data Interpreter example
Agenticness: Guided Assistant

Executes tasks you assign, one step at a time, within narrow domains.

High evidence
Last evaluated: May 23, 2026
This tool has strong action capabilities but limited safety controls. Use with appropriate oversight.

Dimension Breakdown

Action Capability
Autonomy
Planning
Adaptation
State & Memory
Reliability
Interoperability
Safety
Operator Sovereignty

Categories

Pricing
  • Free / open source — full functionality available at no cost.
Details
AddedMarch 26, 2026
RefreshedMarch 28, 2026
Agenticness
Quick Facts
DeploymentSelf-hosted
AutonomySemi-autonomous
Model supportMulti-model
Open sourceYes
Team supportIndividual only
Pricing modelFree / open source
Interfacecli, api
Stay in the loop

Get the weekly agentic AI briefing

New tools, top picks, and trends — delivered every Thursday.

I use AI for: