ROMA is an open-source framework for building high-performance multi-agent systems. It uses a recursive, hierarchical structure to break down complex problems, enabling agents to solve sophisticated tasks with full transparency.
Hi everyone!
I use Gemini's Deep Research every day. It's my go-to after trying all the other deep research tools out there. So, I was pretty shocked when I saw ROMA, an open-source framework, not just competing with, but significantly outperforming top commercial systems on some tough benchmarks.
ROMA is an open-source framework for building these kinds of multi-agent systems. Because it's open, you can plug in any model you want, local or API, and connect your own data sources to build custom agents.
The official examples already show its potential: a general task solver, a deep research agent, and a finance agent. That finance agent idea is pretty interesting for building high-net-worth products. An AI Buffett, maybe? :P
