hmokiguessNvidia NemoClaw
Am I missing something? Why is everyone talking about sandboxes when it comes to OpenClaw?
To me it's like giving your dog a stack of important documents, then being worried he might eat them, so you put the dog in a crate, together with the documents.
I thought the whole problem with that idea was that in order for the agent to be useful, you have to connect it to your calendar, your e-mail provider and other services so it can do stuff on your behalf, but also creating chaos and destruction.
And now, what, having inference done by Nvidia directly makes it better? Does their hardware prevent an AI from deleting all my emails?
Yes, although what I think is different in this setup here is the OpenShell gateway override, as they mention:
> NemoClaw installs the NVIDIA OpenShell runtime and Nemotron models, then uses a versioned blueprint to create a sandboxed environment where every network request, file access, and inference call is governed by declarative policy. The nemoclaw CLI orchestrates the full stack: OpenShell gateway, sandbox, inference provider, and network policy.
I think this means you get a true proxy layer with a network gateway that let's you stop in-flight requests with policies you define, so it's not their hardware but the combination of it plus OpenShell gateway and network policies.
I also think the reason they are doing this is to try and get some moat around these one-clik deployments and leverage their GPU for rent type of thing instead of having you go buy a mac mini and learn "scary" stuff (remember, the user market here is pretty strange lol)
OpenShell is the gem here indeed. A lot of good ideas like network sandbox that does TLS decryption and use of policy engine to set the rules. However:
> Credentials never leak into the sandbox filesystem; they are injected as environment variables at runtime.
If anyone from the team is reading - you should copy surrogate credentials approach from here to secure the credentials further: https://github.com/airutorg/airut/blob/main/doc/network-sand...
The LLM will easily leak these credentials out. So the creds should be outside the sandbox, and the only thing the sandbox should see is a connection API that opens a socket/file handle.
Alternatively where is needs an API key, it should be one bound to the endpoint using it. E.g. a ticket granting ticket is used to create a bound ticket.
A copy on write filesystem would be an interesting way to sandbox writes, but there is difficulty in checking the diff.