By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Devcontainers, VMs, and disposable environments

Running an agent in a container or VM caps the damage at that environment and whatever credentials you put in it. Devcontainers make the setup reproducible, while microVMs and user-space kernels add stronger isolation for untrusted workloads. Isolation is what makes unattended modes defensible.

Read in this order

  1. OfficialClaude Code: Development containersStart here: a ready container setup for running an agent with less risk.
  2. OfficialDocker SandboxesDocker's purpose-built sandboxes for agents, with isolation tradeoffs.
  3. OfficialDevelopment Containers specificationThe devcontainer spec, for making environments reproducible across teams.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.