Live data from Hacker News

Cloudflare OS: an open platform for agents, apps, and work

blog.cloudflare.com

61–70 of 365 posts

Re: Cloudflare OS: an open platform for agents, apps, and work

#61
post #32
post #4

I liked Kenton's take on this: https://x.com/KentonVarda/status/2084990137180590572?s=20 Text from tweet: Today we are releasing Cloudflare OS, a chatbot with connectors, just like every other tech company is doing. Except actually, it's different. This is a remake of Sandstorm[.]io, my startup from 10 years ago, except this time built on Cloudflare Workers (the platform I've spent the last 9 years building) and deep…

That should have been the announcement. The article posted buries the lead. Cloudflare OS reads like almost any other AI knowledge base until midway when apps are introduced and then becomes overly technical with a code snippet.

Random trivia (and something I learned this way myself from an internet reply, though I can't remember when):

What gets buried is the "lede". It is a really unusual thing — a deliberate, engineered misspelling of "lead" that leaked into broader use:

https://www.merriam-webster.com/wordplay/bury-the-lede-versu...

(Not meant as a nit-pick — it's just something that adds really fascinating historical colour to a useful expression, that people often mistakenly re-correct)

Re: Cloudflare OS: an open platform for agents, apps, and work

#62

Why are companies slapping "OS" in their product naming? it's stupid

Because AI enables a new layer more akin to an actual OS. But also because I imagine they all want all the things running through them and an OS is the widest net they can cast in that direction.

Re: Cloudflare OS: an open platform for agents, apps, and work

#65
post #41

Earlier quoted context omitted.

See my next tweet in the chain: https://x.com/KentonVarda/status/2084990302784307363 ------------- Of course, personal apps are more useful if they can connect to external services. Cloudflare OS introduces a "connector" system we call Gatekeepers. This is sort of like MCP (and MCP is supported as a kind of Gatekeeper), but with a lot more: * Instead of exposing tools, a Gatekeeper exposes a Cap'n Web RPC API. That m…

> * When an action requires approval, the agent does not need to stop and wait for it. A Gatekeeper will simulate the outcome, allowing the agent to keep running and queue up more work. You can then approve everything in a batch at the end. Hopefully, this means you no longer feel the need to turn on auto-approve! (But you still can if you want.) Can you say more about how you simulate outcomes of approvals? For exam…

Reads do not require approval. Only writes do.

Reads are, however, limited to only the resources you have explicitly attached.

Moreover, since agents and gadgets run in a sandbox with essentially no access to the outside world except via approved channels (Gatekeepers), it's essentially not possible for the agent to leak secrets it has seen unless you approve a later write.

In fact, the system actually keeps track of everything the agent / gadget has observed to know if it is "tained", and can use that to flag later actions as dangerous, e.g. due to prompt injection or possible leaking of secrets. (This is still evolving, but all the groundwork is there.)

(Of course, this assumes you trust the LLM provider itself not to steal secrets from your prompts. Most LLM providers offer zero-data-retention options, but if you don't trust them you can also use a local LLM. We support ollama and will support others in time.)

Re: Cloudflare OS: an open platform for agents, apps, and work

#66
post #41

Earlier quoted context omitted.

See my next tweet in the chain: https://x.com/KentonVarda/status/2084990302784307363 ------------- Of course, personal apps are more useful if they can connect to external services. Cloudflare OS introduces a "connector" system we call Gatekeepers. This is sort of like MCP (and MCP is supported as a kind of Gatekeeper), but with a lot more: * Instead of exposing tools, a Gatekeeper exposes a Cap'n Web RPC API. That m…

> * When an action requires approval, the agent does not need to stop and wait for it. A Gatekeeper will simulate the outcome, allowing the agent to keep running and queue up more work. You can then approve everything in a batch at the end. Hopefully, this means you no longer feel the need to turn on auto-approve! (But you still can if you want.) Can you say more about how you simulate outcomes of approvals? For exam…

The key aspect here is "when an action requires approval". i.e. an action which writes. Presumably you are granting the read access when firing this process off in the first place.

Re: Cloudflare OS: an open platform for agents, apps, and work

#68
post #53
post #49

Earlier quoted context omitted.

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!”

> 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…

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.

Re: Cloudflare OS: an open platform for agents, apps, and work

#69
post #24

"OS for work" - like, what does it mean? OS is operating system, it runs on a hardware and provides you to operate the system. I hate when companies destroy the English language with vibe invented terms.

If this succeeds, it's going to be in spite of its branding and marketing.
Post reply on HN