Ajeet Singh Raina

I’ve been in the Docker community since 2015.

You already know what is inside your container image.

Early this year, Anthropic shipped Claude Code Remote Control: you start a "remote control" session on your laptop, and then send it prompts from the Claude Code web, iOS, or desktop app.

Docker Sandboxes (sbx) runs AI coding agents inside isolated microVMs.

Claude Code, like most agentic coding tools, asks for permission before it does anything consequential: editing a file, running a shell command, installing a package, or making a network call.

When I first joined Docker as a full-time employee in 2022, I came across something called Whaleness Day.

Docker Sandboxes (sbx) runs AI coding agents inside isolated microVMs.

AI coding agents are useful precisely because they act on their own.

Docker Sandboxes (sbx) runs AI coding agents inside isolated microVMs each agent gets its own Docker daemon, filesystem, and network, so it can build images, install packages, and rewrite files without ever touching your host.

Running large language models locally used to mean juggling Python environments, CUDA toolkits, model-conversion scripts, and a different serving stack for every model format.

Most developers running Claude Code today run it directly on their host machine.

💡 Updated for sbx v0.37.0-rc1.

Stay ahead with curated insights on Docker, Kubernetes, IoT, and emerging AI technologies delivered straight to your inbox.

When you hand a coding agent your repository, you're also handing it your shell.

The Problem Statement You want to run an AI coding agent inside a Docker Sandbox.