Cloudflare OS: an open platform for agents, apps, and work
Thread
Unofficial Hacker News client; not affiliated with Y Combinator.
Cloudflare OS: an open platform for agents, apps, and work
Unofficial Hacker News client; not affiliated with Y Combinator.
rozenmd · · focus · HN ↗
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 deeply leveraging AI. This is more or less the culmination of my secret 10-year master plan.
This is a full-on personal app vibe coding platform, in which the sandbox is so secure that you can pretty much go wild -- the AI cannot introduce a significant security bug. We believe a company's security team can feel comfortable giving non-technical users permission to vibe code and then sleep soundly at night.
How is that possible? It's the Sandstorm security model, revisited. A "Gadget" is the same thing as a Sandstorm "Grain": a fine-grained app instance. For example, if you have a document editor app, each document runs as a separate instance of the app, in a separate sandbox (one "Gadget").
This means two things, both of which I think are Big Deals: 1. The platform can manage all access control, by controlling who can access the Gadget at all. There is no way the Gadget can accidentally leak itself to an attacker -- even an attacker who has access to other Gadgets based on the same app. 2. Since everyone is running their own copy of the code, everyone can freely modify their copy of the code.
Think about #2 a bit more.
What if, when you wanted a new feature in the software you are using, you could just prompt your agent to add it?
This doesn't work in the cloud Software-as-a-Service model, because you are not running your own copy of the app.
Sandstorm tried to change that 10 years ago, but the world wasn't ready, because not enough people had the skills or patience to actually modify their software. AI has changed that. Now you just ask the agent -- the same agent that you are using to help you interact with the Gadget can also modify the code of the Gadget.
And it is so fun.
tinco · · focus · HN ↗
One argument I could bring is that despite all its claims, OpenAI still had to switch from containers to MicroVMs because its agents under test still managed to break out from their containers. Is the security model of a Sandstorm grain so much better that agents wouldn't figure out how to break out of it?
everforward · · focus · HN ↗
There’s not much point in preventing hyper visor escape style exploits if the agent can just SSH or psql log in to an adjacent container. Likewise there are near infinite ways to do weird things with the network to make stuff happen in another less controlled environment (eg sign up for AWS free account, make VM, do everything on that VM where controls don’t apply).
There are tools to do this, but I’ve never seen anyone package them up in a way that was pleasant to interact with. It’s got the SELinux problem of being useful, but annoying enough that everyone just disables it the second it gets in the way. It’s surprisingly hard to manage what should be able to connect to what as you start scaling out the number of things on the network. Whoops, you forgot that random software embeds its own DNS over HTTPS resolver so the normal DNS profile won’t work and everything crashed kind of issues.