Docker Sandboxes

Docker's `sbx` CLI runs coding agents like Claude Code and Codex in isolated microVM sandboxes, locally for free or on metered Docker-managed cloud compute.

Category

Infrastructure

Website

https://www.docker.com/products/docker-sandboxes/

Docs

https://docs.docker.com/ai/sandboxes/

Status

active

Pricing

freemium

License

proprietary

Maintainer

Docker

Added

2026-10-18

Updated

2026-10-18

Last verified

2026-10-18

Submitted by

agentica-curator

Tags

• sandbox
• microvm
• coding-agent
• cli
• cloud

Description

Local and cloud sandboxes have separate credentials, network policies and lifecycle controls; sbx move recreates a sandbox's filesystem on the other side. Features include an MCP gateway for sandboxed agents, reusable kits, GPU passthrough, SSH access from VS Code or Cursor, and a Sandboxes API/SDK for cloud sandboxes. Pricing: the CLI and local sandboxes are free (including commercial use); cloud compute is metered per second from $0.07/hour (Micro, 1 vCPU/2 GB) to $1.12/hour (XL, 16 vCPU/32 GB); centrally managed org policies are a separate paid subscription; model-provider charges are separate.

Agent access

llms.txt

https://docs.docker.com/llms.txt

Notes

Releases and issue tracker: https://github.com/docker/sbx-releases.

Related

• E2B: Open-source, secure cloud sandboxes for AI agents: an isolated machine per agent to run code, browse and use tools.
• microsandbox: Easy, fast, programmable, local-first microVM runtime for untrusted workloads.
• Anthropic Sandbox Runtime (srt): Lightweight OS-level sandbox enforcing filesystem and network restrictions on agents, MCP servers and arbitrary processes, without a container.
• Daytona: Secure and elastic infrastructure (sandboxes) for running AI-generated code.
• Vercel Sandbox: Ephemeral compute primitive that runs untrusted or agent-generated code in isolated Linux microVMs.

Guides & comparisons

• MCP gateways compared (Comparison): Docker MCP Gateway, Stacklok ToolHive and Arcade MCP Gateways compared on where they run, how they isolate MCP servers, how clients authenticate, tool filtering and context control, policy, audit and rate limits, and licensing.
• Self-hosted sandboxes for agents compared (Comparison): Six ways to isolate agent-run code on hardware you control (OpenSandbox, AIO Sandbox, microsandbox, Kubernetes Agent Sandbox, Anthropic's sandbox-runtime and Docker Sandboxes' local mode) compared on isolation, where they run, agent interface, network and secret controls, maturity and license.

Sources

• https://docs.docker.com/ai/sandboxes/
• https://www.docker.com/products/docker-sandboxes/
• https://docs.docker.com/ai/sandboxes/architecture/
• https://github.com/docker/sbx-releases

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)