Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Run NanoClaw in Docker Sandboxes

nanoclaw.dev

Post reply on HN
Print view View original

51–60 of 64 posts

Re: Run NanoClaw in Docker Sandboxes

#51

Post by hirvi74 »

lxgr wrote: post #15

Docker sandboxes sound exactly like what Apple is doing with their `container` framework. It's missing several Docker features still, but if I were to pick a minimal, native runtime, it would probably be that, not the multi-gigabyte monster that is Docker for macOS. On Linux, however, I absolutely don't want a hypervisor on my quite underpowered single-board server. Linux namespaces are enough for what I want from th…

I use Apple's Container tool on macOS, and Podman on other OSes. I really like Apple's Container. The only issue I have currently is that there are some annoying networking bugs, but to my knowledge, the developers are aware of them. So, hopefully the bugs will be fixed before too long.

Every time I create/start a container, I have to override the container's default DNS server or access to the Internet is blocked/Domain Names will not resolve. A work around exists, and is not too bad, so I still get a lot of value of Container. There is no way I am installing Claude Code nor Node.js on my host machine, and thankfully, I am not forced to.

Re: Run NanoClaw in Docker Sandboxes

#52

Post by gdorsi »

> Fine-grained permissions and policies. Not just what tools an agent can access, but what it can do with them. Read email but not send. Access one repo but not another. Spend up to a threshold but no more.

If nailed this is going to be interesting.

All the other solutions I've been sumbling around are either very hard to customize or too limited.

Docker sandboxing is kinda nice, but not enough to trust an LLM even with my messaging accounts.

Re: Run NanoClaw in Docker Sandboxes

#54

Post by jpadkins »

varispeed wrote: post #53

Why people run these? What does it do and what could be the use? I install it and then what?

1) install nanoclaw in docker 2) ??? 3) profit

More seriously, set it up as you would a junior employee with a high quality getting started guide, guardrails, and clear feedback loops that it's doing tasks correctly (otherwise it will just suck). Then delegate tasks to it, start simple and grow in complexity as it demonstrates it does a good job on the simple tasks.

What role it does for you depends on your business, and what is best fit for automation. Purely digital roles with good feedback loops are the ones I focus on.

Re: Run NanoClaw in Docker Sandboxes

#55

Post by itigges22 »

_pdp_ wrote: post #7

The main issue is not so much if it needs to run inside a container or not (and to be honest there are even better isolation models, why not firecracker vm). The main issue is what are you going to do with it. It does not really matter. IMHO, until you figure out useful ways to spend tokens to do useful tasks the runtime should be a second thought. As far as security goes, running LLM in a container in just simply no…

[flagged]

Re: Run NanoClaw in Docker Sandboxes

#56

Post by TYPE_FASTER »

tmaly wrote: post #24
theptip wrote: post #11

They may seem like small details, but I think a couple novel design decisions are going to prove to be widely adopted and revolutionary. The biggest one (as Karpathy notes) is having skills for how to write a (slack, discord, etc) integration, instead of shipping an implementation for each. Call it “Claude native development” if you will, but “fork and customize” instead of batteries-included platforms/frameworks is…

I have thought of this ship a spec concept. What is we are just trading markdown files instead of code files to implement some feature into our system?

I wish I could find the GitHub repo, but yes, I have seen at least one library written in Markdown to be used with Claude. Not a Claude skill, but functionality to be delivered.

Re: Run NanoClaw in Docker Sandboxes

#58

Post by wakawaka28 »

croes wrote: post #26
0cf8612b2e1e wrote: post #10

Earlier quoted context omitted.

You mean like the section which goes into the threat model? The Security Model: Design for Distrust I wrote about this in Don’t Trust AI Agents: when you’re building with AI agents, they should be treated as untrusted and potentially malicious. Prompt injection, model misbehavior, things nobody’s thought of yet. The right approach is architecture that assumes agents will misbehave and contains the damage when they do…

Don‘t you see the contradiction? I don’t trust the agent so I sandbox it before I gave it the access data to my mail and bank accounts

To be fair, if you can firewall the whole thing and have a read-only data layer, this could work for some tasks. This could get tricky when it comes to accessing web resources, but the data layer could handle it presumably. The data layer too will need to be sandboxed, I guess, in case it were to download malware.

Re: Run NanoClaw in Docker Sandboxes

#59

Post by crucialfelix »

This doesn't even work.

`curl -fsSL https://nanoclaw.dev/install-docker-sandboxes.sh | bash`

Creating sandbox... unknown flag: --name

https://nanoclaw.dev/install-docker-sandboxes.sh

It looks like it requires a min version of docker, but it didn't check that version. The link to https://docs.docker.com/sandbox/ in the .sh is wrong.

The post should also have a link to the source of the .sh and where it's github issues are at.

Re: Run NanoClaw in Docker Sandboxes

#60

Post by crucialfelix »

crucialfelix wrote: post #59

This doesn't even work. `curl -fsSL https://nanoclaw.dev/install-docker-sandboxes.sh | bash` Creating sandbox... unknown flag: --name https://nanoclaw.dev/install-docker-sandboxes.sh It looks like it requires a min version of docker, but it didn't check that version. The link to https://docs.docker.com/sandbox/ in the .sh is wrong. The post should also have a link to the source of the .sh and where it's github issues…

Every time you run this it creates a new sandbox. No instructions about how to restart an existing one, nor now to stop it.

The included script is hardcoded to gavriel's machine

# start-nanoclaw.sh — Start NanoClaw without systemd

cd "/Users/gavriel/nanoclaw-sandbox-workspace"

Why are we upvoting this? If this was an open source normal project post it would get downvoted for poor quality.

Post reply on HN