Yolobox Configurator
Generate .yolobox.toml configs and CLI commands visually
terminal
# Install yolobox
$ brew install finbarr/tap/yolobox
# Let your AI go full send
$ yolobox claude
> Container ready. AI has sudo. Home directory is safe.AI Agent
Choose which AI coding agent to run inside the sandbox
Select Agent
Host Forwarding
Forward credentials and sockets from your host machine
Security & Isolation
Control how locked down the container environment is
Resource Limits
Set CPU, memory, shared memory, and GPU constraints
Container Runtime
Choose runtime engine and custom image options
Advanced Configuration
Packages, mounts, environment variables, and Linux capabilities
Container IsolatedFull Sudo AccessHome Directory Safe
yolobox \
claude \
--git-config \
--gh-tokenAPI Keys Auto-Forwarded
These environment variables are automatically passed to the container if set on your host:
ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY,
GH_TOKEN, OPENROUTER_API_KEYHow to Configure a Yolobox Sandbox
- 1
Select your AI agent
Choose which AI coding agent will run inside the sandbox: Claude Code, Codex CLI, Gemini CLI, Aider, or a custom command. The tool generates agent-specific configuration. - 2
Configure forwarding options
Enable forwarding for git config, GitHub tokens, SSH agent, Docker socket, or agent-specific config files. This gives the sandboxed agent access to credentials it needs without exposing your full home directory. - 3
Set security modes
Toggle security options: require confirmation for commands (no-yolo), make the project read-only, disable network access, or start with a scratch filesystem. - 4
Adjust resource limits
Set CPU cores, memory, shared memory size, and GPU access. This prevents runaway processes from consuming host resources. - 5
Copy the CLI command or TOML config
Switch between the CLI tab for a one-line command or the Config tab for a .yolobox.toml file. Place the TOML file in your project root for persistent configuration.
Common Use Cases
1
Running Claude Code Safely
Give Claude Code full permissions inside a container while keeping your home directory, SSH keys, and system files completely isolated from any agent actions.
2
Testing Untrusted Code Changes
Let AI agents write and execute code in a sandboxed environment. If something breaks, discard the container and start fresh — your real project is untouched.
3
Team-Shared Agent Configurations
Commit a .yolobox.toml file to your repository so every team member runs AI agents with identical security settings, resource limits, and forwarding rules.
Why Use the Yolobox Configurator?
Yolobox is a CLI tool that runs AI coding agents like Claude Code, OpenAI Codex, and Google Gemini inside isolated Docker containers. The AI gets sudo access and full freedom to install packages, write files, and run commands — while your home directory stays completely protected. This configurator helps you visually build .yolobox.toml project files and generate ready-to-use CLI commands without memorizing every flag and option.
Whether you're setting up resource limits, forwarding SSH keys, adding custom packages, or configuring network isolation, this tool generates the exact configuration you need. It supports all yolobox features including multiple container runtimes (Docker, Podman, Apple containers), GPU passthrough, read-only project mounts, and custom Dockerfile fragments.
The Yolobox Configurator is a visual tool for generating .yolobox.toml configuration files and CLI commands for yolobox, an open-source container sandbox designed to run AI coding agents safely. AI coding assistants like Claude Code, OpenAI Codex, Google Gemini CLI, and Aider often need broad system permissions to install packages, write files, and execute commands. Yolobox solves the security tension by giving the AI full sudo access and auto-approval mode inside an isolated Docker container while keeping your home directory, SSH keys, and system files completely protected. This configurator lets you visually build configurations covering agent selection, host credential forwarding (git config, GitHub tokens, SSH agent, Docker socket), security modes (read-only project mounts, network isolation, scratch sessions), resource limits (CPU, memory, shared memory, GPU passthrough), container runtime selection (Docker, Podman, Apple containers), and advanced options like APT packages, extra mounts, environment variables, and Linux capabilities. The tool outputs both a one-line CLI command for quick use and a .yolobox.toml file for persistent project-level configuration that can be committed to your repository for consistent team-wide settings. All configuration is generated entirely in the browser with nothing sent to any server. The configurator covers every yolobox flag and option so you do not need to memorize CLI arguments.
Frequently Asked Questions
1
What is yolobox?
Yolobox is an open-source CLI tool that runs AI coding agents inside isolated containers. It gives the AI full sudo access and auto-approval mode while protecting your home directory and system files from accidental damage.
2
Which AI agents does yolobox support?
Yolobox supports Claude Code (with --dangerously-skip-permissions), OpenAI Codex, Google Gemini CLI, GitHub Copilot, and OpenCode. You can also run any custom command inside the container.
3
Is yolobox safe to use?
Yolobox provides container-level isolation that protects against accidental filesystem damage. Your home directory is unmounted by default. For maximum security, use rootless Podman or VM-level isolation.
4
Where does the .yolobox.toml file go?
Place .yolobox.toml in your project root directory. It configures project-specific settings like extra packages, mounts, environment variables, and network isolation. Global settings go in ~/.config/yolobox/config.toml.
5
Do I need Docker installed?
Yes, yolobox requires a container runtime. Docker is the default, but it also supports Podman and Apple's container runtime. Install Docker Desktop or use rootless Podman for enhanced security.
Related Tools
Loadbalancer Design
Developers
Json Formatter
Developers
Json Minifier
Developers
Json Escaper
Developers
Url Params To Json
Developers
Json To Url Params
Developers
Json Path Finder
Developers
Json To Html Form
Developers
Json To Tailwind Form
Developers
Json To Bootstrap Form
Developers
Json To React Form
Developers
Form To Json Schema
Developers