Docker Sandboxes – Disposable, isolated sandboxes for AI agents

Docker Inc. has launched Docker Sandboxes, a new product that provides disposable, isolated microVM environments for AI coding agents such as Claude Code, Gemini CLI, Copilot CLI, Codex, OpenCode, and Kiro, enabling safe unattended execution. The sandboxes offer customizable network and filesystem controls, hard security boundaries from the host, and support for agents to spin up containers within them. Docker Sandboxes can be installed via Homebrew with 'brew trust docker/tap && brew install docker/tap/sbx' and are available for individual developers, with Docker AI Governance offering centralized controls for teams.

Run AI agents safely in local sandboxes. Claude Code, Gemini CLI, Copilot CLI, Codex, OpenCode, and Kiro that need safe, unattended execution. Sandboxes in action. Get started in seconds. brew trust docker/tap && brew install docker/tap/sbx Give agents the autonomy they need to get work done, safely. Need to enforce these controls across your whole team? That’s Docker AI Governance /products/ai-governance/ YOLO mode, safely. Customizable Safe Execution Network and filesystem controls you define. MicroVM Isolation Hard security boundary from the host. Fast to Spin Up, Easy to Tear Down Disposable by default. Faster than VMs. Agents Can Use Docker Too Agents can spin up containers within Sandboxes. Real Dev Environment Install packages, run services, work unattended. One Sandbox for All Your Coding Agents Claude Code, Gemini CLI, Copilot CLI, Codex, Kiro, OpenCode. Works with leading coding agents Common questions. What is a sandbox for AI coding agents? A sandbox is a microVM isolated environment that protects your filesystem and network from agents running inside it. Which coding agents are supported? Out of the box we support Claude Code, Gemini CLI, Copilot CLI, Codex, OpenCode, Kiro. You can also create your own What does “YOLO mode” mean, and is it safe? YOLO mode --dangerously-skip-permissions gives agents autonomy with no approval prompts. Essential for speed, but risky without guardrails. Sandboxes make it safe by isolating each agent inside a dedicated microVM. How is a sandbox different from a VM? Sandboxes run fully isolated in microVMs, giving more isolation without paying the full cost of running a VM. This lets them do things that need more permissions safely, like running additional Docker containers. What safety controls can I configure? To define these once and enforce them on every developer’s machine, see Docker AI Governance https://www.docker.com/products/ai-governance/ . Do I need Docker Desktop to use sandboxes? No. What if I need additional admin controls? Installing Sandboxes covers core functionality. For centralized controls across a team such as network policies, filesystem rules, MCP governance: Docker AI Governance https://www.docker.com/products/ai-governance/ . Need More Control Over Your Sandboxes? Docker AI Governance https://www.docker.com/products/ai-governance/ adds network access policies, filesystem controls, and org-wide MCP governance: defined once, enforced everywhere. Talk to us about: - Network access policies for sandbox environments - Filesystem access controls and restrictions - Admin-level configuration for your team