All directories
AgentEngineeringProduct

MetaGPT

FoundationAgents/MetaGPT

Multi-agent “AI software company” — roles collaborate to generate software artifacts. GitHub: FoundationAgents/MetaGPT (~70k stars).

Open on GitHubBrowse more agents
00

GitHub repository

https://github.com/FoundationAgents/MetaGPT
01

Overview

MetaGPT (FoundationAgents/MetaGPT) is listed in LimeDock Directories as an AI agent resource. Multi-agent “AI software company” — roles collaborate to generate software artifacts. Group: multi-agent. Community size: ~70k GitHub stars. Repo (copy/paste): https://github.com/FoundationAgents/MetaGPT This page is a plain-English guide so searches for the GitHub project can land on how teams actually use it.

SaaSOther

Work with LimeDock

Using this skill? LimeDock can wire it into a durable automation you own.

Agents are a starting point. LimeDock turns the workflow into production automation your SaaS team owns — not another prompt library.

We sell owned automations for SaaS teams — live workflows that plug into Slack, CRM, and your internal platform — not just a skill list.

Book a workflow call
02

Link

https://github.com/FoundationAgents/MetaGPT
03

Installation guide

Open the GitHub repository, then follow the README for your stack.

Official GitHub repository: https://github.com/FoundationAgents/MetaGPT GitHub path: FoundationAgents/MetaGPT

How to open it: 1. Copy: https://github.com/FoundationAgents/MetaGPT 2. Clone or follow the README for your OS/stack. 3. Start with the smallest example before production use.

04

How to use it

**Simple example** You want to see multi-agent role play (PM/eng/QA) produce a software plan/code sketch.

1. Install MetaGPT. 2. Run a simple product requirement through the company roles. 3. Treat output as draft — human-architect the real system.

05

Example prompts

  • “Run MetaGPT on a one-paragraph product idea.”
  • “MetaGPT vs ChatDev vs CrewAI?”
  • “What should humans still decide?”
06

Use cases and examples

  • Evaluate FoundationAgents/MetaGPT as an AI agent building block
  • Pilot MetaGPT on one staging workflow
  • Compare against agents you already pay for
  • Document a team playbook after the pilot
07

Prerequisites

  • Python env
  • LLM keys
08

Tips

  • Great for drafts, not autopilot shipping.
  • Constrain scope tightly.