Running NanoClaw in a Docker Shell Sandbox (opens in new tab)

I think it's funny that we're moving in the direction of providing extremely fine-grained permissions models to serve AI and prevent it from accessing things it should not - but that's a level of control we will never have (or even expect to have) over third parties that use our sensitive data.

Yes please! I feel like we need filters for everything: file reading, network ingress egress, etc Starting with simpler filters and then moving up the semantic ones…

ExoAgent (from your bio/past comments) looks really interesting. Godspeed!

So basically WAF, but smarter :)

Maybe this is just me, but you'd think at some point it's not really a "sandbox" anymore.

And how are you going to define what ocaps/flows are needed when agent behavior is not defined?

you have to reference Royal food tasting somehow. just saying

At first glance, this feels like just an internal testing prompt at their company for some sort of sales pipeline. Feels more like an accident. None of the referenced files are actually in the repository. If the prompts had more of a "If the user mentions xyz, mention our product" that would absolutely give more credence that this is an advertising prompt, but none of that is here.

Oof

Kata containers are the right way to go about doing sandboxing on K8s. It is very underappreciated and, timing-wise, very good. With ec2 supporting nested virtualization, my guess is there is going to be wide adoption.

Woah, that looks great. I’ve been looking for something like this. Neither thr readme or the security doc go into detail on the credential handling in the gateway. Is it using tokens to represent the secrets, or is the client just trusting that the connection will be authenticated? I’m trying to figure out how similar this is to something like Fly’s tokenizer proxy.

I'm still not that interested in setting up openclaw, but this implementation actually looks/sounds pretty good.

Thanks for sharing!

Yeah, we are on it. In the current version, things are hardcoded and implicit (we are also in experimental preview), but soon it will be configurable and explicit.

good catch, it's naturally `ANTHROPIC_API_KEY`, but I could have been more specific.

> The docs is so messy and the whole process was unstable.

What do you expect? the entire app is vibed.

Docker Sandboxes are microVMs.

Basically due to many reasons, ld_preload, various containers standards, open desktop, current init systems, widespread behavior from containers images from projects, LSM limitations etc…

It is impossible to maintain isolation within an agentic environment, specifically within a specific UID, so the only real option is to leverage the isolation of a VM.

I was going to release a PoC related to bwrap/containers etc… but realized even with disclosure it wasn’t going to be fixed.

Makes me feel bad, but namespaces were never a security feature, and the tooling has suffered from various parties making locally optimal decisions and no mediation through a third party to drive the ecosystem as a whole.

If you are going to implement isolation for agents, I highly suggest you consider micro VMs.

You cannot execute (docker) containers securely within another container which also limits what you can do with any agent (DinD). A coding agent that generates a `Dockerfile` would surely benefit from starting a container with it. And generally speaking, as a another commenter explained, name-spacing does not give you the full host isolation that you are looking for when running truly untrusted code which is the reality when using agents.

I strongly believe that we will see MicroVMs becoming a staple tool in software development soon, as containers are never covered all the security threats nor have the abilities that you would expect from a "true" sandbox.

I wrote a blog post that goes a bit into detail [1].

Let's see whether Docker (the company) defines this tooling, but I'd say that they are on a good path. However in the end I'd expect it to be a standalone application and ecosystem, not tied to docker/moby being my container runtime.

[1] https://sourcediver.org/posts/260214_development_sandboxes/

First thing I heard about it too, apparently docker has VMs now?

> Each agent runs inside a dedicated microVM with a version of your development environment and only your project workspace mounted in. Agents can install packages, modify configs, and run Docker. Your host stays untouched. - https://www.docker.com/products/docker-sandboxes/

I'd assume they were just "more secure containers" but seems like something else, that can in itself start it's own containers?

+1. It is confusing.

LocalGPT uses Landlock LSM.

It's a bad approach, it can still see the / directory, and eventually you want to give it sudo privilege or act as the root user to get anything done. Yet I really wouldn't trust these things as far as I could throw them, there is no "undo" button in the terminal.

I was like you with docker at the start of the week, I had managed to avoid it until now, but I didn't want to let agents do crazy sneaky stuff to my main system. VirtualBox, even with the guest additions just sucks as an environment to spend more than a few hours developing in, especially with how they take up precious RAM and VRAM that local LLMs need. Let me tell you: Docker for this use case at least turned out to be way easier than I thought! It only took me a few hours to really understand the main workflow for a basic project, docker is actually very nice to use, I should not have left it this long. With just a few commands I feel like I got enough sandboxing for my liking. For example, from my bash history yesterday:

    docker run -it --rm archlinux

this gives you an interactive archlinux container, and destroys itself when you exit with ctrl+d. If you want to re-enter where you left off, you can attach or start the container again if you omit the --rm flag.

    docker build -t flask_test .

this builds a container tagged "flask_test" using Dockerfile in the current directory. Dockerfiles are quite simple

    FROM python:3-alpine

    WORKDIR /my_app

    RUN pip install flask
    # copy app.py from the working directory to the container directory "."
    COPY app.py . 

    # Make port 5000 available to the world outside this container
    # this networking stuff is a bit of a mess to configure, you have to set it in flask, the Dockerfile, when you run the container, and you still get different URLs that the server is on, not all work on the host or the container, etc., it's a bit of a mess IMO. This turned out to not be necessary. 
    #EXPOSE 5000

    # Define environment variable for Flask
    ENV FLASK_APP=app.py

    ENV FLASK_RUN_HOST=0.0.0.0

    # run the command "flask" when the container starts with the "run" argument
    CMD ["flask", "run"]

The docs are very extensive, and feature a lot of (for me, anyway) useless commands like

    "docker ps"
    "docker images"

these are not that useful compared to this:

    docker container ls --all

which just shows everything.

Then, to restart from where you exited the next day:

    docker start -ia amazing_jemison 

This resumes the "amazing_jemison" (randomly assigned name) container. You see the name under column in the previous ls --all command. I don't get why they use CONTAINER IDs so much in the docs instead of NAMES, because they don't feature tab autocomplete, requiring wasted effort copying long hexadecimal strings.

I've been using throwaway archlinux docker containers all week, it's like a snappy VM, I just have to figure out how to launch graphics applications, although apparently that's an antipattern. I tried alpine, ubuntu, debian, etc., too, but archlinux is what I'm used to and the perfect balance between size and being feature-complete for me. Alpine boasts about the minimal image size but in reality you end up missing a lot of useful modern premium features that you have to redownload anyway. I never made a Dockerfile for it, it just downloaded the default archlinux image. After you exit out, and it selfdestructs with rm, and then you want to do it all again from scratch, as per the first command

    docker run -it --rm archlinux

and it will use a locally cached version, saving Docker from having to redownload

Overall a very good experience.

This is my take.

First: the audience is NOT software devs. Because as you've surely noticed if you are a software dev, you can do most of the things that OpenClaw can do; if it offers improvements, they seem very marginal. You know, "it makes web apps" I can do that; "it posts to Discord programmatically" I can code that; etc. Maybe an AI code buddy shaves a few minutes off but so what. It's hard to understand the hoopla if this is you.

However, if you're a small business owner of some kind, where "small business" is defined by headcount (not valuation - this can include VC's), it's been transformative.

For a person like that, adding a 10k/mo expense is a natural move. And, at that price point, an AI service for 2k/mo is more than competitive: it's a savings.

The other part is that I think a lot of people have gotten used to human-in-the-loop workflows, but there's a big step up if you can omit the person.

Combining this w/the observation above, there were a lot of small business owners who were probably stymied by this problem: they had a bunch of tasks across departments that were worth like $2k/mo to do but couldn't fill (not enough in salary, couldn't be local). AI fits naturally for that use case. For them, it's valuable.

I'm wondering the same thing. I keep seeing examples like "book your plane tickets" and "reschedule your meetings". I don't know who does these relatively high stakes things often enough to automate them.

I see the value for managing software projects, but the personal assistant stuff I don't get. Then again, I would never trust a model to send an email on my behalf, so I'm probably not the target audience.

A CEO answered on Twitter:

> Mine runs my auto parts company.. tracks 395K products on Amazon, manages 3 warehouses, scrapes competitor pricing, handles email, posts to social media

https://x.com/BrianRoyBarber/status/2023389093648884000

PS: Also, this is wild!

> What this does: apiKeyHelper tells Claude Code to run echo proxy-managed to get its API key. The sandbox’s network proxy intercepts outgoing API calls and swaps this sentinel value for your real Anthropic key, so the actual key never exists inside the sandbox.

I recently started experimenting with agents and found this sandboxing tool for OpenCode useful https://github.com/glennvdv/opencode-dockerized

Crazy isn't it? The first commit on nanoclaw is 2 weeks ago and it already got a front page blog post from docker.com and they shipped first class feature to host it. You don't get much more peak-hype than this.

I don’t think SV is hyping Claw are they? Claw is all open source and indy. SV would much rather you use some YC service which does one thing Claw does, or use the LLM’s own dedicated 1P agent framework.

I get why you feel this way. There's this weird thing happening online where AI hype accounts dog pile on any hint of the beginning of a trend and will beat on it until the next trend comes around. They will make up claims and create endless content in the format that they discovered is effective.

This makes it really difficult to understand what's real and what's hype. It feels like everything that's trending is BS because of the obvious boosting and exaggeration.

But there are real, noteworthy things that are happening and they get mixed in with a lot of BS.

Coding agents being massive amplifiers of skilled developers productivity is not hype. There are countless 10s or maybe 100s of thousands of developers who have built things that they simply wouldn't have been able to do a few years ago. It doesn't matter what that MITRE study says if you've built something with your own hands that wouldn't have existed without AI.

Bringing the same coding agents to regular people on WhatsApp and Telegram, and connecting it with enough apps and data sources so it can do valuable work is a massive unlock of value. There is massive hype around it, but underneath all the hype there is something big and real. I am getting immense value from this. I recommend that you put your skepticism on hold for a short time and give it a real try. Real is key. If you go in trying to prove your skepticism right, you will be able to do that. But if you approach with curiosity you'll undoubtedly discover ways you can start extracting value from it

the big labs talk about curing cancer - Altman, Hassabis, Musk

the little guys hype Claw

> What happened to curing cancer?

Because being a cancer is more, well, metastasizing.

Remember, that capitalism is growth at all costs, until the host is dead, aka cancer.

And, fake money until you can be money?