Show HN：Yolobox – 在不危及家目錄的情況下，以完整 sudo 權限運行 AI 編碼代理

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Let your AI go full send. Your home directory stays home.

License

Uh oh!

There was an error while loading. Please reload this page.

finbarr/yolobox

Folders and files

Latest commit

History

Repository files navigation

Let your AI go full send. Your home directory stays home.

Run Claude Code, Codex, or any AI coding agent in "yolo mode" without nuking your home directory.

The Problem

AI coding agents are incredibly powerful when you let them run commands without asking permission. But one misinterpreted prompt and rm -rf ~ later, you're restoring from backup (yea right, as if you have backups lol).

The Solution

yolobox runs your AI agent inside a container where:

The AI can go absolutely wild inside the sandbox. Your actual home directory? Untouchable.

Quick Start

Then from any project:

You're now in a sandboxed shell. Run claude and let it rip.

What's in the Box?

The base image comes batteries-included:

Need something else? You have sudo.

AI CLIs Run in YOLO Mode

Inside yolobox, the AI CLIs are aliased to skip all permission prompts:

No confirmations, no guardrails—just pure unfiltered AI, the way nature intended.

Commands

Flags

Auto-Forwarded Environment Variables

These are automatically passed into the container if set:

Configuration

Create ~/.config/yolobox/config.toml for global defaults:

Or .yolobox.toml in your project for project-specific settings:

Priority: CLI flags > project config > global config > defaults.

Note: Setting claude_config = true in your config will copy your host's Claude config on every container start, overwriting any changes made inside the container. Use the CLI flag --claude-config for one-time syncs.

Runtime Support

Memory: Claude Code needs 4GB+ RAM allocated to Docker. Colima defaults to 2GB which will cause OOM kills. Increase with: colima stop && colima start --memory 8

Threat Model

What yolobox protects:

What yolobox does NOT protect:

For extra paranoia, use --readonly-project to mount your project read-only. Outputs go to /output.

Building the Base Image

This builds yolobox/base:latest locally.

Why "yolobox"?

Because you want to tell your AI agent "just do it" without consequences. YOLO, but in a box.

License

MIT

About

Let your AI go full send. Your home directory stays home.

Resources

License

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

  1

Packages

  0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

  2

Languages

Footer

Footer navigation