Commands

Default workflow

yolobox is built around AI shortcut commands:

yolobox claude
yolobox codex
yolobox gemini
yolobox opencode
yolobox copilot

That is the intended path. You point the agent at a project and let it work inside the sandbox.

Command reference

AI shortcuts

yolobox claude
yolobox codex
yolobox gemini
yolobox opencode
yolobox copilot

These launch the matching tool inside yolobox and apply the tool-specific YOLO-mode wrapper when one exists.

General commands

yolobox                     # Open an interactive shell
yolobox run <cmd...>        # Run a single command in the sandbox
yolobox setup               # Write global defaults to ~/.config/yolobox/config.toml
yolobox config              # Print the resolved config for the current project
yolobox upgrade             # Update the binary and pull the latest base image
yolobox reset --force       # Remove yolobox named volumes
yolobox uninstall --force   # Remove yolobox binary, image, and volumes
yolobox version             # Print version and platform
yolobox help                # Show CLI help

Common examples

Start an agent with Docker access

yolobox claude --docker --git-config --gh-token

Run one command in isolation

yolobox run --no-network --readonly-project python3 untrusted_script.py

Build with extra packages for one project

yolobox run --packages default-jdk,maven mvn --version

Inspect the resolved configuration

yolobox config

Reset persistent state

yolobox reset --force

Mental model

Use shortcut commands when you want an AI agent session.

Use run when you want one exact command in the same sandbox model.

Use the bare yolobox shell when you are debugging or exploring manually, not as the main path.