aktech

AI Sandbox — DevOps skill for Claude Code

DevOps community

Per-project Docker sandbox for AI coding agents like Pi and Claude Code.

How to install AI Sandbox

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aktech/ai-sandbox and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Sandbox does

Per-project Docker sandbox for AI coding agents like Pi and Claude Code.

Alternatives in DevOps

Claude Code Router — Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the m 30.1k ★
Cccc — Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your p 1.1k ★
Claudebox — A Claude Code Docker Development Environment for running Claude AI's coding assistant in a fully containerized 964 ★

README

ai-sandbox

[![ci](https://github.com/aktech/ai-sandbox/actions/workflows/ci.yml/badge.svg)](https://github.com/aktech/ai-sandbox/actions/workflows/ci.yml) [![image](https://github.com/aktech/ai-sandbox/actions/workflows/image.yml/badge.svg)](https://github.com/aktech/ai-sandbox/actions/workflows/image.yml) [![release](https://github.com/aktech/ai-sandbox/actions/workflows/release.yml/badge.svg)](https://github.com/aktech/ai-sandbox/actions/workflows/release.yml)

Run AI coding agents (Claude Code, Codex, pi, etc.) in a Docker container instead of directly on your laptop. Each project gets its own container, and the container can only see the folders you explicitly mount in. If the agent goes wrong, you lose the container — not your home directory.

The CLI is called `aisb`. One command spins up (or re-enters) a sandbox for the current project and drops you into a shell where `claude`, `codex`, and `pi` are already installed.

![architecture](docs/architecture.svg)

Getting started

You need Docker running. On macOS, [colima](https://github.com/abiosoft/colima) works well (`colima start`). Nothing else: you do not need to clone this repository or install Go.

**1. Install `aisb`.** Download the binary for your machine from the [latest release](https://github.com/aktech/ai-sandbox/releases/latest), check its checksum, and put it on your `PATH`:

OS=$(uname -s | tr '[:upper:]' '[:lower:]')
ARCH=$(uname -m | sed 's/x86_64/amd64/; s/aarch64/arm64/')
F=aisb-$OS-$ARCH
curl -fsSLO "https://github.com/aktech/ai-sandbox/releases/latest/download/$F.tar.gz"
curl -fsSLO "https://github.com/aktech/ai-sandbox/releases/latest/download/$F.tar.gz.sha256"
if command -v sha256sum >/dev/null; then sha256sum -c "$F.tar.gz.sha256"; else shasum -a 256 -c "$F.tar.gz.sha256"; fi   # must print: OK
tar -xzf "$F.tar.gz"
mkdir -p ~/.local/bin && install -m 0755 "$F" ~/.local/bin/aisb
aisb help                               # if "command not found": add ~/.local/bin to your PATH