If it's a codex alternative why can't I just use my codex subscription with it for cloud inference? Why can't I just use my open router keys? Why is your business model being an inference proxy?

I am also building a very similar thing for myself, a runtime to unify the agent + application logic. Currently I am in the process of migrating from single agent on electron only to multi agent + web host. I have some big ideas I am dreaming up, but when it comes down to it the guiding force is just me building what I think would be cool to have.

Why is the app closed source if it's meant as a platform for building desktop apps on? What does your application-on-chatoss distribution model look like?

▲

thetjmccarty 21 hours ago | parent [-]

If you sign up for the $8/m Starter plan, you can use any OpenAI compatible keys. So your OpenRouter keys would work.

The business model choice is what made sense to try out right now. It also makes it easy to get up and running with open source cloud models.

If you build an application that runs on ChatOSS, you own the app, it doesn't belong to ChatOSS. You can do whatever you want. You could create an app for the platform that you charge a subscription fee for or offer for free or whatever you want.

	▲	hankbond 21 hours ago \| parent [-]
		> You could create an app for the platform that you charge a subscription fee for or offer for free or whatever you want. Interesting choice, I was thinking of a similar thing (if I ever decided to monetize) but instead take a cut of app sales (by providing the distribution channel) and having no base usage fee (for the desktop version). For the hosted version it would cost some amount bc it's hosted in a remote VM for the user. I guess in that way it would make sense to offer some amount of inference with the price for users that don't have an existing codex subscription (and non-technical users would never have an open router key anyway).