← The ShowroomAgent infrastructure

Writeup only

modelPlayground

An offline AI setup: local models, a chat window, a coding helper, and a switch to cloud models.

Status
Working
Built with
Ollama, Open WebUI, Aider, llama.cpp, Bash
Last worked on
2026-10

What it is

modelPlayground is our kit for running open AI models on a home computer with the network off, and switching to cloud models when we choose. One command starts a chat window in the browser, with offline search over your own documents, and another command shuts it down to free memory. Coding helper scripts work fully local, fully cloud, or hybrid, where a cloud model plans and a local model makes the edits. A "rainy day" guide covers what to do when cloud AI services are down. It is personal infrastructure, not a product anyone else can install yet.

How it works

  1. Run the start command; the chat window opens on the local machine.
  2. Pick a local model and chat, or ask questions about documents in the offline library.
  3. For coding, launch the coding helper in local, cloud or hybrid mode.
  4. Run the stop command to free memory when done.

What exists today

What isn't there yet

Under the hood