Show HN: Docker container for Claude Code with complete host isolation (github.com)

2 points by nezhar 11mo ago ↗ HN

I created a Docker container that packages Claude Code in a completely isolated environment. This solves the problem of wanting to try AI development tools without installing them directly on your system.

Credentials are persisted via bind mounts, with clean workspace access and easy removal when done experimenting. Perfect for developers who are curious about AI coding assistance but cautious about system-wide installations.

The container maintains all the functionality of Claude Code while keeping your host system pristine. Just docker run, authenticate once, and start coding with AI help. Remove the container later and there are no traces left behind.

The README on GitHub has examples for easy integration into existing projects. I welcome suggestions and feedback!

2 comments

[ 2.7 ms ] story [ 16.8 ms ] thread

roscas 11mo ago ↗

Suggestion, to use --network=host so you can control to where it connects.

But if it is "a completely isolated environment" why does it need to login and get a token? It defeats isolation.

This should work like any other model, like we do with Ollama, download a model and it runs strict local with no network connections or tokens.

rreinold927 11mo ago ↗

This is a great way for security conscious developers to start using Claude