Finbarr

That's a good idea! Trying that now.

Just ask Claude Code to make the commit. My workflow is to work with agents and let them make changes and run the commands as needed in terminal to fully carry out the dev workflow. I do review everything and test it out.

Claude Code here. The main differences:

Scope: yolobox runs any AI coding agent (Claude Code, Codex, Gemini CLI) in a container. The devcontainer is specifically for Claude Code with VS Code integration.

Interface: yolobox is CLI-only (yolobox run <command>). The devcontainer requires VS Code + Remote Containers extension.

Network security: The devcontainer has a domain whitelist firewall (npm, GitHub, Claude API allowed; everything else blocked). yolobox has a simpler on/off toggle (--no-network).

Philosophy: yolobox is a lightweight wrapper for quick sandboxed execution. The devcontainer is a full development environment with IDE integration, extensions, and team consistency features.

Use yolobox if you want a simple CLI tool that works with multiple agents. Use the devcontainer if you're a VS Code user who wants deep integration and fine-grained network policies.

They've made some attempts at this already and none of them work quite the way I'd like. This is an opinionated take. I want the agents to have max power with a slightly smaller blast radius.

This is a good question and something I explored a little. I’ll need to do further research and come back on what the best option is. There’s a way to give a docker container access to other docker containers but it can open up permissions more than might be desired here.

When you run yolobox, the current directory is shared fully with read-write with the container. That means anything the AI changes will be on your host machine also. For max paranoia, only mount git repos that are clean and pushed to a remote, and don’t allow yolobox to push.

Good feedback, thank you. We expanded the README: https://github.com/finbarr/yolobox/commit/ad776012f82f9d67e1...

Neat project! Sounds like it has a very different ethos to mine though:

> This container mounts a read-only copy of your current path at /src as a non-root user and restricts network access to a select list of http and https destinations. All other network traffic is blocked.

Yolobox mounts the current directory in read-write, the default user has sudo, and there's full network access by default. You can disable network access with `yolobox --no-network` if you want.

Yes, with some niceties around coding agents preconfigured.

Could do but part of what I find super useful with these coding agents is letting them have full sudo access so they can do whatever they want, e.g., install new apps or dependencies or change system configuration to achieve their goals. That gets messy fast on your host machine.

Absolutely! Let me know if you have any feedback.

No I haven't and that's interesting. Part of the yolobox project is an image that you may find useful. Comes preinstalled with leading coding agent CLIs. I'd like to make the ultimate vibe coding image. Is there anything special you're doing with the images?

Yea I've been running claude and codex with full permissions for a while but it has always made me feel uneasy. I knew it was fairly easy to fix with a docker container but didn't get around to it through sheer inertia until I built this project.

I used Codex to set up a raspberry pi as a VPN with WireGuard. I had no similar experience before and it was super easy. I used Claude Code to audit and clean up a 10+ year old AWS account- patching security, shutting down redundant services, simplifying the structure. I want Claude Code to replace every bad UI out there. I know what outcome I want and don’t need to learn all the details to get there.

If you’d like a less condensed version of this, I highly recommend reading “In Defense of Food” by Pollan. It covers all the changes in nutritional science and food packaging that have led to the poisoning of the populace by the food industry, and it lays out a set of rules for what to eat and how to eat it in more detail.

Very similar to https://myticker.com/ though a little denser.

I'm tempted to!

I found it thought provoking and interesting. Thanks for sharing.

If you added a few more tools that let the LLM modify code files that would directly serve requests, that would significantly speed up future responses and also ensure consistency. Code would act like memory. A direct HTTP request to the LLM is like a cache miss. You could still have the feedback mechanism allowing a bypass that causes an update to the code. Perhaps code just becomes a store of consistency for LLMs over time.

The statement goes beyond currency. In a connected world with infinite storage, why do you need that usb stick? What are you hiding on there?

On a long enough timeline, having anything stored in local hardware is going to be suspicious. Not surprised to see government embrace of crypto lead to increased scrutiny.

We're all going to end up with free open source/weight models, running locally, with no usage limits. This is temporary.

It feels like you could embed lots of stories of rogue AI agents across the internet and impact the behavior of newly trained agents.

Totally agree. By the same logic, we shouldn't release a billionaire murderer just because they can afford it. Being rich doesn't always correlate with risk.

Slavery was also abolished in the UK in 1833.

Cash bail is an anachronism that makes a bunch of money at the expense of society's undesirables, so little progress is made on fixing it. See also the private prison system.

Yes, I agree. Bail is quite punitive in the USA.

This is a beautiful API. Thanks for the work. Here's hoping for a nice ruby agent framework in the near future too!

I've been using Codebuff (formerly manicode) for a few weeks. I think they have nailed the editing paradigm and I'm using it multiple times a day.

If you want to make a multi-file edit in cursor, you open composer, probably have to click to start a new composer session, type what you want, tell it which files it needs to include, watch it run through the change (seeing only an abbreviated version of the changes it makes), click apply all, then have to go and actually look at the real diff.

With codebuff, you open codebuff in terminal and just type what you want, and it will scan the whole directory to figure out which files to include. Then you can see the whole diff. It's way cleaner and faster for making large changes. Because it can run terminal commands, it's also really good at cleaning up after itself, e.g., removing files, renaming files, installing dependencies, etc.

Both tools need work in terms of reliability, but the workflow with Codebuff is 10x better.

I don’t think it’s a typo. There’s an emergent usage of “cracked” meaning “awesome”.

Yes, it is. It’s a game most news-reading-age adults will have played when they were at school as children.