← Back to context

Comment by tokenless

1 day ago

Openclaw!

You can sandbox anything yourself. Use a VM.

It has a web ui.

Yeah I think this is gonna have to be the approach. But I don't like the fact that it has all the complexity of a baked in sandboxing solution and a big plugin architecture and blah blah blah.

TBH maybe I should just vibe code my own...

I don’t really understand the point of sandboxing if you’re going to give it access to all your accounts (which it needs to do anything useful). It reminds me of https://xkcd.com/1200/

  • Because you don't give it access to all your accounts, you choose what. And files on your PC may be private and you don't want to risk exposing them.

    A use case may be for example give it access to your side project support email address, a test account on your site and web access.

  • Yeah I have been planning to give it its own accounts on my self hosted services.

    I think the big challenge here is that I'd like my agent to be able to read my emails, but... Most of my accounts have Auth fallbacks via email :/

    So really what I want is some sort of galaxy brained proxy where it can ask me for access to certain subsets of my inbox. No idea how to set that up though.

    • > So really what I want is some sort of galaxy brained proxy where it can ask me for access to certain subsets of my inbox. No idea how to set that up though.

      Though of the same idea. You could run a proxy that IMAP downloads the emails and then filters and acts as IMAP server. SMTP could be done the same limited to certain email addresses. You could run an independent AI harmful detector just in case.