Coding agents like Claude Code, Gemini CLI, Codex, Kiro, and OpenCode are changing how developers work. But as these agents become more autonomous (capable of deleting repos, modifying files, and accessing secrets), developers face a real problem: how do you give agents enough access to be useful without risking your local environment?<\/p>\n
Today, development with coding agents means picking your poison:<\/p>\n
We think developers need a better option. So we\u2019re experimenting with a solution that could give you both safety and productivity.<\/p>\n
We\u2019re working on an approach that lets you run coding agents in purpose-built, isolated local environments. Docker Sandboxes wrap agents in containers that mirror your local workspace and enforce strict boundaries across all the coding agents you use. The idea is to give agents the access they need while maintaining isolation from your local system.<\/p>\n
Today\u2019s experimental release runs agents as containers inside Docker Desktop\u2019s DockerVM. This provides security through filesystem isolation and process containment. We\u2019re moving towards a microVM-based architecture for even stronger isolation and safety.<\/p>\n
This is an experimental preview. Commands may change and you shouldn\u2019t rely on this for production workflows yet. But we\u2019re excited about where we\u2019re heading.\u00a0<\/p>\n
Here\u2019s what you get today:<\/p>\n
OS-level sandboxing approaches like Linux Bubblewrap or macOS seatbelt have significant limitations:<\/p>\n
Container-based isolation is designed for exactly the kind of dynamic, iterative workflows that coding agents need. You get flexibility without brittleness.<\/p>\n
We\u2019re taking a usability-first approach. Rather than trying to be a great solution for all kinds of AI out of the box, we\u2019re focusing specifically on coding agents. This lets us solve real developer problems and deliver a great experience. We\u2019ll support other use cases in the future, but for now, coding agents are where we can make the biggest impact.<\/p>\n
Today\u2019s experimental preview works natively with Claude Code and Gemini CLI. We\u2019re building for other agents developers use.<\/p>\n
With Docker Desktop 4.50 and later installed, run: That\u2019s it. Your agent runs in an isolated environment and you stay productive.\u00a0<\/p>\n We\u2019re building this alongside developers. As you experiment with Docker Sandboxes, we want to hear about your use cases and what matters most to your workflow.<\/p>\ndocker sandbox run <agent><\/code><\/p>\nWhat\u2019s Next.<\/strong><\/h3>\n
\n
Try It and Share Your Feedback.<\/strong><\/h3>\n