So you can run it off the public internet with no sneaky external dependency on cloudflare, slack etc?

And it would be functionally the same? With the same performance if you put enough hardware there?

If so cool, and that should have been clearly in the announcement, because as it sounded it is “I am a sucker, lock me in!”

▲

kentonv 6 hours ago | parent | next [-]

> So you can run it off the public internet with no sneaky external dependency on cloudflare, slack etc?

Yes. It even supports ollama and works decently well with some local LLMs.

> And it would be functionally the same? With the same performance if you put enough hardware there?

Honestly it is faster running locally.

> If so cool, and that should have been clearly in the announcement,

We had so many things we wanted to say, it was hard to fit them all into one story.

The blog post is for an enterprise audience. My tweet thread is for the hacker audience.

▲

mosura 6 hours ago | parent | next [-]

That is actually cool.

Maybe it is my bubble, but the experience people are having with Anthropic particularly is motivating a big “get this stuff back under control” effort so while it may not be strategically optimal for Cloudflare the local hosting would prove more valuable to enterprises than maybe a few years back, even if presented as a backup plan.

▲

edaemon 5 hours ago | parent | prev [-]

Neat! How does that work with the AI Gateway portion? I see some references in the code but at a quick glance I can't tell if you can configure it to skip AI Gateway.

	▲	kentonv 5 hours ago \| parent [-]
		Use of Cloudflare AI Gateway is optional. In the default configuration, you just plop your Anthropic/OpenAI/Gemini/Workers AI/ollama API keys into the UI and it talks to each provider directly. That said, I would recommend AI Gateway, it has a lot of nice features. :)

▲

upcoming-sesame 5 hours ago | parent | prev [-]

You're not alone The name "cloudflare-os" by itself made me think this was heavily based on Cloudflare