Building Openbench, a local-first LLM workspace

I've been using local LLMs for a while now, but the tools still feel rough. Ollama makes running models easy. However, when you want to do than just a basic prompt, like comparing two models, refining a system prompt, or checking what was actually sent, you end up piecing things together. So, I started building Openbench. What it is This is a desktop app for experimenting with local models. It’s not just another chat wrapper; it’s of a workspace. The goal is to focus on prompt iteration, model comparison, and being able to see what’s happening under the hood.