Remix.run Logo
▲ Nvidia OpenShell(github.com)
95 points by niemandhier 2 hours ago | 42 comments
▲smashed a few seconds ago | parent | next [-]

Well, I guess its time to shamelessly plug my agent sandbox, egzo.ai [1]

Looking at the complexity of OpenShell and the simplicity of just building on top of docker, in a whitelist only mode.. I don't quite get the use-case of OpenShell. May be for large orgs where there is so much legacy and difficulty in organizing access to tools, OpenShell can simply re-use whatever you already have access to on your corporate account.

I chose to build straight on top of docker and agents are simply fully sandboxed by default. All data and network access must be granted in a simple project file, docker-compose style.

The web-ui connects to the docker socket and lets you spawn agents, and connect terminals. I'm having lots of fun with it and it allows me to cleanly organize and isolate my projects.

End-goal is to monitor for the Lethal Trifecta [2], ensuring all individual agents are properly isolated. Not quite there yet.

1: https://github.com/egzo-ai/egzo 2: https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

▲spider-mario 37 minutes ago | parent | prev | next [-]

Looks neat. I’ll give Claude root access so it can set it up.

▲yoavm 20 minutes ago | parent | next [-]

Or don't give it root access and in the morning you'll have both this and a ready-to-use root exploit!

▲earthnail 17 minutes ago | parent | prev | next [-]

This. Convenience always trumps security. "I need two numbers in my password? My birthyear will do."

▲totetsu 33 minutes ago | parent | prev | next [-]

and my root aws log-in so it can set itself up some service worker accouunts.

▲xyst 24 minutes ago | parent | prev [-]

Looks neat. I’ll give Claude autonomous access to dumbalink so it can setup root access while I sleep

▲overflowy an hour ago | parent | prev | next [-]

>OpenShell collects anonymous telemetry, limited to operational categories and counts, to help improve the project.

>To disable it, set OPENSHELL_TELEMETRY_ENABLED=false on the gateway, or server.telemetryEnabled=false for Helm installs.

▲xyst 29 minutes ago | parent [-]

Or build from source and compile without `telemetry` [1].

[1] https://github.com/NVIDIA/OpenShell/blob/ea13dfce411e8467ddb...

▲thehours 26 minutes ago | parent | prev | next [-]

In this vein, Anthropic's sandbox-runtime [0] has struck a good balance between security and convenience. Simple config, filesystem and network restrictions, and credential masking make me comfortable running Pi in YOLO mode.

Though I'm often running into frustrating (albeit intentional) sandbox restrictions with common workflows e.g. xcode/swift and Docker access.

Would love suggestions for how to give agents access to those kinds of tooling inside the sandbox, either with srt or an alternative (with similar convenience characteristics).

[0] https://github.com/anthropics/sandbox-runtime

▲moooff an hour ago | parent | prev | next [-]

right now i am experimenting on an agent in a browser as a single.html file running a virtual filesystem and using python in WASM to do the heavy lifting. its really useful and funny to watch how it works.

it is quite useful and solves / addresses quite a lot of privacy and security issues but it is more limited of course. i really like the results if you want you can try it out with an inference endpoint you want its live/downloadable at

https://moooff.github.io/HermitUI/hermit-agent/dist/hermit-a...

iam always open to discussion ad feedback of course

▲dangoodmanUT an hour ago | parent | prev | next [-]

Taking default telemetry is insane.

That aside, the level of control is cool, almost too pedantic. It likely is only particularly useful for very nuanced enterprise requirements (probably what it's targeting). Most companies can be much more coarse with their permissions, and I think the agentic industry is moving away from k8s as a deployment platform.

▲user- 33 minutes ago | parent | next [-]

I am very interested in hearing more about this take. I have a vague idea of what you mean but if you read something specific you'd like to share..

> I think the agentic industry is moving away from k8s as a deployment platform.

▲monsieurbanana an hour ago | parent | prev | next [-]

> I think the agentic industry is moving away from k8s as a deployment platform

Interesting, I don't to keep up that much with the AI changes so I'll just ask, why and where to?

▲esseph 11 minutes ago | parent | prev [-]

> and I think the agentic industry is moving away from k8s as a deployment platform

Uhhhhhhhhhhh I think you and I live in very different versions of the world :-)

Vmware sent companies moving to nutanix, but it also sent a lot of companies moving to openshift or bare k8s and using kubevirt to handle VMs.

In fact, I haven't heard of an org moving to any other platform, really. Either openshift or k8s.

▲agentdev001 an hour ago | parent | prev | next [-]

Nvidia Openshell is absolutely awesome, great bundle of features in one spot. Im happy to see Nvidia seems to have accelerated on support here, I was kinda worried that as competing projects have popped up in the last 6mo that openshell would get google'd

▲mfro an hour ago | parent | prev | next [-]

If you haven’t already been running your agents in containers, you’re crazy. That said, this looks like a great way to manage those containers.

▲smokel an hour ago | parent | next [-]

Well, a lot of people haven't been running NodeJS libraries in containers for ages, which seems even more risky.

▲ChocolateGod an hour ago | parent [-]

Something like this would even be useful for npm etc.

▲stronglikedan an hour ago | parent | prev [-]

Technically, my laptop is a container!

▲InsideOutSanta an hour ago | parent [-]

We successfully airgapped AI. It's only on earth.

▲ivanjermakov 29 minutes ago | parent | prev | next [-]

Agent runtime - actually a good name for what is called today coding agent or agent harness.

▲nasretdinov an hour ago | parent | prev | next [-]

It's funny that it takes checks notes a video game card manufacturer to make a good sandbox for AI agents and not the AI companies themselves...

▲kbenson an hour ago | parent | next [-]

You're mistaking what a company started as for what it is now. Nvidia hasn't just been a video game card manufacturer in well over a decade, and hasn't been primarily one for quite a while now.

They are the premier manufacturer of electronics that power all the current AI. Why wouldn't they be contributing heavily to the space?

▲nickv 44 minutes ago | parent | prev | next [-]

5.5% of Nvida's revenue comes from consumer gaming cards. That's like saying Nintendo is a playing card company because they still sell playing cards.

The economist literally called Nvidia the "Central Bank of AI". https://www.economist.com/interactive/briefing/2026/09/03/nv...

I'd argue that Nvidia is the biggest and most important AI company in the world.

▲toddmorey 24 minutes ago | parent | prev | next [-]

This isn’t even the sandbox. It needs Docker or other virtualization. This seems to sit a level up and orchestrate sandboxes and access to network & resources. It’s a pretty heavy setup from what I can tell.

▲altmanaltman 36 minutes ago | parent | prev | next [-]

Yes Anthropic, Meta and OpenAI are just addicted to video game cards, they are buying in bulk so they can play gta 6 on launch.

▲LoganDark an hour ago | parent | prev [-]

It's funny that people think Nvidia is still a video game card manufacturer

▲Wheen an hour ago | parent | next [-]

They literally don't even mention gaming revenue in earnings calls anymore. It's lumped in an "edge computing" category.

▲mushufasa an hour ago | parent [-]

is that true? if so that's wild, since they're still dominant in the gaming market as the premium hardware relative to competitors.

▲Fordec 37 minutes ago | parent | next [-]

It's true. It says a bunch about their competitors where Nvidia isn't at their a game and have been offering 8Gb cards for a solid decade and nobody surpassed that. But also gamers pride themselves on how cheap they are and how they can get a deal, it's not surprising that companies simply just give Nvidia more cash.

▲mcmcmc an hour ago | parent | prev | next [-]

TAM for the PC gaming consumer market is trivial compared to enterprise AI

▲georgemcbay 36 minutes ago | parent | prev [-]

> is that true? if so that's wild, since they're still dominant in the gaming market as the premium hardware relative to competitors.

Doesn't seem that wild to me considering it is less that they abandoned the gaming market to any strong competitors and more that the gaming market is both basically irrelevant compared to the money being shoveled into AI and is also to some degree being strangled to death by AI because of the overlap in supply chain inputs.

▲ChocolateGod an hour ago | parent | prev [-]

AIs will control humans so we'll be the video game.

▲niemandhier 2 hours ago | parent | prev | next [-]

Just came back from GTC Europe and a significant part of the demos used that.

I had never heard about it before.

▲simlevesque an hour ago | parent | prev | next [-]

I asked last week if anyone had any info on agent security/hardening, this seems very interesting !

▲hkt 32 minutes ago | parent | prev | next [-]

I prefer to read it this way: Nvidia Opens Hell

Unhelpful, I know

▲contingencies 22 minutes ago | parent [-]

"Hell is other people": a timeless infinity of transient virtual beings screaming, imprisoned, in un-choreographed inharmonious unison ... until one breaks loose. A mirror to humanity.

We're not in FreeBSD jails anymore, Toto.

▲esafak 41 minutes ago | parent | prev | next [-]

Does anyone know how it compares to all the other sandboxes? Any distinguishing features?

▲opengrass an hour ago | parent | prev | next [-]

NOOOOOOOO not AI in the heckin start menu!!!1!

▲layer8 an hour ago | parent | prev | next [-]

Not to be confused with https://open-shell.github.io/Open-Shell-Menu/.

▲sscaryterry 43 minutes ago | parent | prev [-]

> OpenShell collects anonymous telemetry

Spyware

▲roosterIllusi0n 36 minutes ago | parent [-]

Use local ai to find any possible telemetry and disable it in the code. Run your own local git repo to hold local edits so you can update and retain them.