I’ve been running Clawdbot for the last couple weeks and have genuinely found it useful but running it scares the crap out of me.

OpenClaw has 52+ modules and runs agents with near-unlimited permissions in a single Node process. NanoClaw is ~500 lines of core code, agents run in actual Apple containers with filesystem isolation. Each chat gets its own sandboxed context.

This is not a swiss army knife. It’s built to match my exact needs. Fork it and make it yours.

> running it scares the crap out of me

A hundred times this. It's fine until it isn't. And jacking these Claws into shared conversation spaces is quite literally pushing the afterburners to max on simonw's lethal trifecta. A lot of people are going to get burned hard by this. Every blackhat is eyes-on this right now - we're literally giving a drunk robot the keys to everything.

This look nice! I was curious about being allowed to use a Claude Pro/Max subscription vs an API key, since there's been so much buzz about that lately, so I went looking for a solid answer.

Thankfully the official Agent SDK Quickstart guide says that you can: https://platform.claude.com/docs/en/agent-sdk/quickstart

In particular, this bit:

"After installing Claude Code onto your machine, run claude in your terminal and follow the prompts to authenticate. The SDK will use this authentication automatically."

One of the things that makes Clawdbot great is the allow all permissions to do anything. Not sure how those external actions with damaging consequences get sandboxed with this.

Apple containers have been great especially that each of them maps 1:1 to a dedicated lightweight VM. Except for a bug or two that appeared in the early releases, things seem to be working out well. I believe not a lot of projects are leveraging it.

A general code execution sandbox for AI code or otherwise that used Apple containers is https://github.com/instavm/coderunner It can be hooked to Claude code and others.

I feel like a lot of non technical people who are vibe coding or vibe using these models, focus on hallucinations and believe that as the hallucinations are reduced in benchmarks, and over estimate their ability to create safe prompts that will keep these models in line.

I think most people fail to estimate the real threat that malicious prompts can cause because it is not that common, its like when credit cards were launched, cc fraud and the various ways it could be perpetrated followed not soon after. The real threats aren’t visible yet but rest assured there are actors working to take advantage and many unfortunate examples will be seen before general awareness and precaution will prevail….

Thanks! Was hoping someone would do something more sane like this.

Openclaw is very useful, but like you I share the sentiment of it being terrifying, even before you introduce the social network aspect.

My Mac mini is currently literally switched off for this very reason.

I think these days if I’m going to be actively promoting code I’ve created (with Claude, no shade for that), I’ll make sure to write the documentation, or at the very least the readme, by hand. The smell of LLM from the docs of any project puts me off even when I like the idea of the project itself, as in this case. It’s hard to describe why - maybe it feels like if you care enough to promote it, you should care to try and actually communicate, person to person, to the human being promoted at. Dunno, just my 2c and maybe just my own preference. I’d rather read a typo-ridden five line readme explaining the problem the code is there to solve for you and me,the humans, not dozens of lines of perfectly penned marketing with just the right number of emoji. We all know how easy it is to write code these days. Maybe use some of that extra time to communicate with the humans. I dunno.

Edit: I see you, making edits to the readme to make it sound more human-written since I commented ;) https://github.com/gavrielc/nanoclaw/commit/40d41542d2f335a0...

Interesting choice to use native Apple Containers over Docker.

I assume this is to keep the footprint minimal on a Mac Mini without the overhead of the Docker VM, but does this limit the agent's ability to run standard Linux tooling? Or are you relying on the AI to just figure out the BSD/macOS equivalents of standard commands?

If you run openclaw on a spare laptop or VM and give it read only access to whatever it needs, doesn’t that eliminate most of the risk?

Can we start putting disclaimers beside the title on AI-generated projects? Extremely fatiguing to read through it and realize it’s mostly LLM slop.

To be honest, when I see many vibecoded apps, I just build my own duplicate with Claude Code. It's not that useful to use someone else's vibecode. The idea is enough, or the evidence that it works for someone else means I can just build it myself with Claude Code and I can make it specific to my needs.

  Quick Start
  git clone https://github.com/anthropics/nanoclaw.git

Or is this just so hastily thrown together that the Quick Start is a hallucination?

That's not a facetious question, given this project's declared raison d'etre is security and the subtle implication that OpenClaw is an insecure unreviewed pile of slop.

I like the idea of a smaller version of OpenClaw.

Minor nitpick, it looks like about 2500 lines of typescript (I am on a mobile device, so my LOC estimate may be off). Also, Apple container looks really interesting.

Can you use MCP tools? I saw that with open claw they moved away from that which I personally didn't like but

The singularity, but instead successive exponential improvement, its excessive exponential slop which passes the Turing test for programmers.

lol, I might finally have to upgrade my Mac mini to Tahoe. Yofi.