Show HN: Containerized AI development with cross-compatibility

A developer released a containerized AI development template on GitHub that uses Docker and VS Code to isolate AI harness CLIs, aiming for cross-compatibility across Linux, MacOS, and WSL2. The project, which leverages PI.dev's coding agent, seeks to reduce token usage and enable skill installations while protecting the host system from destructive AI commands.

I need to study different harnesses CLI, and to find a way to switch from one provider to another. I built a template repository to govern your AI chats with more grip than usual. It leverages PI.dev coding agent and an aggressive isolation done with Docker + VS Code So far works on Linux and MacOS, and should also works on WSL2. The project uses a container to run your preferred AI harnesses CLI. The container is optional, but protect your disk from bad things I noticed rm -rf is always the preferred removal command of Deepseek : a bit scary I am slowly extending it, aiming at - reduce token usage - ability to install extra skill via pi.dev - experimenting with variants like AWS AI-SDLC v1 . Please feel free to comment and give me hints. Comments URL: https://news.ycombinator.com/item?id=48894720 https://news.ycombinator.com/item?id=48894720 Points: 1 Comments: 0