This tool's GitHub repository hasn't had commits in 90+ days. It may be receiving limited maintenance.
MetaGPT is a multi-agent framework that assigns PM, engineer, and QA roles to LLMs, letting them collaborate on software development and produce complete codebases from a single requirement.
Multi-agent framework that assigns PM, engineer, and QA roles to LLMs for collaborative software development. Generates full codebases from a single requirement.
MetaGPT holds a HookFlow heat score of 35/100 in AI Coding Agents, currently showing cooling interest after an earlier surge. Its score has moved +3 points over the last 30 days. On the Lock-In Index it scores 100/100 (high lock-in, with significant switching cost). Note: its public repository has slowed, with no commits in the last 90+ days.
0–100 viral momentum index combining social buzz, search trends & growth velocity
Computed from 5 live sources in the latest pipeline run — more sources, higher confidence.
MetaGPT assigns PM, engineer, and QA roles to LLMs. These agents work collaboratively to handle different aspects of software development.
Yes. MetaGPT generates full codebases from a single requirement by having multiple LLM agents work together in their assigned roles.
MetaGPT is free to use.
A multi-agent framework coordinates multiple AI agents with different roles or specializations to work together on complex tasks. In MetaGPT, agents simulate PM, engineer, and QA functions.
A.R.C. ratings are calculated for developer infrastructure and API-first tools. This tool hasn't been evaluated yet or falls outside the A.R.C. scope.
Lower = more portable. 0 = fully open, 100 = maximum lock-in.
GitHub health score, founder track record, full A.R.C. breakdown, category peer comparison, and 14-day score forecast — in one printable report.
View Full Audit Report