I've been running Claude Code with --dangerously-skip-permissions in a Docker container for the last month or so, allowing me to get up and stretch my legs while it does its thing. I definitely wouldn't want to run it unsandboxed.

▲

SchemaLoad 2 hours ago | parent | next [-]

Sandboxing seems like the obvious solution. These tools prompt me to review an absurd number of very complex bash commands where there is realistically no way to carefully review them. I just want to put the thing in a box with the code and let it run any number of commands on the code without prompting.

▲

eru 2 hours ago | parent [-]

You can actually use a hook to have a script review the (bash) commands for you.

▲

SchemaLoad 2 hours ago | parent [-]

This is still less safe and less convenient than sandboxing. I want them to be able to run whatever command they want inside the sandbox even if it's traditionally dangerous (overwrites files, etc) because it can't touch anything that matters and I can revert any changes to the code myself.

If anything the only thing you'd have to have reviewed is sandbox escape attempts.

	▲	eru 2 hours ago \| parent [-]
		You are right. And the hook is for convenience, not for safety. Having explicit sandboxes is good, of course. But in addition I also treat my whole computer like a sandbox, it least in the sense that there's no files I would mind if they were overwritten or deleted: you should have backups anyway.

▲

franze 3 hours ago | parent | prev | next [-]

I built an (overengineered) app for that AIFCC https://apps.apple.com/app/aifcc-ai-first-computer/id6782364...

runs a sandboxed linux on your mac, and the agents have full system rights within there and run in yolo mode

	▲	Barbing 3 hours ago \| parent [-]
		I like the pitch. Three-month free trial is impressive. Any limitations you were frustrated by releasing it on the App Store? Any drawbacks that you (or other readers) find overall?

▲

lukan 3 hours ago | parent | prev | next [-]

Another nice option to do this while staying in control, is activate /remote-control and approve from mobile while walking around.

▲

konsnos 3 hours ago | parent | prev | next [-]

Can you share your experience? What did you flag during those sessions?

▲

arvyy 2 hours ago | parent | prev | next [-]

same, and unlike other repliers, I'll say one doesn't need to reinvent a new tool for this. Just use devcontainers.

	▲	croemer 2 hours ago \| parent [-]
		Same, I've also been running with `--dangerously-skip-permissions` in devcontainers with docker volumes to keep Claude/Codex auth tokens. Works really well!

▲

allan_s 3 hours ago | parent | prev | next [-]

There's actually a setting.json key to not have to put the option

▲

etoxin 3 hours ago | parent | prev | next [-]

I'm using Docker Sandboxes with a custom Kit. The cli is nice and the TUI is also good. https://docs.docker.com/ai/sandboxes/

▲

jsiepkes 3 hours ago | parent | prev | next [-]

Same here. I use this utility to make it easier on Linux to run Claude in Podman: https://github.com/mismosmi/ai-pod

▲

kmeh 3 hours ago | parent | prev [-]

[dead]