I think it’s pretty clear that the OP meant that a downside of this is that you need a GPU to run it quickly locally, not that it being local first is a bad thing.

To be very clear, I never said open-source is a problem.

In fact, Rubbrband started as an open-source project.

Each member of our team are ML researchers who have committed tens of thousands of lines to open-source.

I think you're conflating open-source with local installations. Our founding team was not fan of the interfaces that a lot of these projects have for our use cases. Not to mention, our hardware just doesn't run them.