Hey guys,
I’ve been messing around with the new Hermes Agent framework lately, trying to test out some multi-agent workflows and complex tool-calling stuff with the Hermes 3 and Llama 3.3 NIMs.
It works great, but the problem is the default 40 RPM limit is killing my workflow rn. Since agents usually chain multiple requests together when they reason or call local tools, I’m constantly getting hit with the “429 Too Many Requests” error after just a few steps. It’s kinda breaking the whole execution loop tbh.
Is it possible to bump my personal account rate limit up to 200 RPM so I can actually finish these development tests?
Also, could you double-check if the “Public API Endpoints” permission is fully active for my organization while you’re at it? Just want to make sure everything’s good to go.
Appreciate the help, thanks a lot!