Isolated environments for coding agents
Govern agents and Claws across every team
Your AI Agent across Docker
- Local-first LLM inference made easy
- Connect and manage MCP tools
- Ship with secure, enterprise-ready images
- Simplify the software supply chain
- Containerize your applications
- Discover and share container images
- Break free of local constraints
- Find guides for Docker products
- Learn the Docker basics
- Search a library of helpful materials
- Skill up your Docker knowledge
- Create and share your own extensions
- Connect with other Docker developers
- Explore open source projects
- Help shape the future of Docker
Docker Sandboxes
Run AI agents safely in local sandboxes.
Disposable, isolated sandboxes for AI agents like Claude Code, Gemini CLI, Copilot CLI, Codex, OpenCode, and Kiro that need safe, unattended execution.
Setup Instructions
macOS
$ brew install docker/tap/sbx
Windows
winget install Docker.sbx
Sandboxes in action.
Watch an agent install packages, run Docker, modify configs, and execute unattended. Then dispose of the sandbox in one command.
sbx-demoRunning...
$ sbx run claude
Starting claude agent in sandbox 'claude-ai-project'...
⣿ Mounting workspace: ~/projects/ai-project
⣿ Network policy: deny all, allow 42 hostnames
Get started in seconds.
macOS
$ brew install docker/tap/sbx
Windows
winget install Docker.sbx
Why sandboxes
Give agents the autonomy they need to get work done, safely.
Agents do their best work when they have freedom. Sandboxes let them run fast without running wild, so speed and safety stop being a tradeoff.
Capabilities
YOLO mode, safely.
Each agent runs inside a dedicated microVM with your dev environment and only your project workspace mounted in. Agents can install packages, modify configs, and spin up their own Docker containers. Your host stays untouched. No manual review, no permission prompts, no supervision required.
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.
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?
Fine-grained control over networking, filesystem permissions, and resource limits — so agents get exactly the access they need and nothing more.
Do I need Docker Desktop to use sandboxes?
No.
Need More Control Over Your Sandboxes?
With Docker Sandboxes, your developers get isolated environments to run agents freely and safely. When your team needs to go further with network access restrictions, filesystem policies, and centralized admin controls, we can help you configure the right setup.