Ask HN: Does a local, Git-backed LLM "compiler" for personal notes make sense?

Back in 2012, my very first startup was a note-taking and document storage app. Think Evernote meets Google Drive, but with a much faster UI. We managed to claw our way up to 1,800 active users. Then Google announced 25GB of free storage for Drive, and overnight, our business model evaporated. We had to shut down the company.

I've been through the startup ringer four times since then. Despite the explosion of knowledge management tools over the last decade, I still manage almost my entire life and todo list in a single Markdown file. I’ve grown to severely distrust SaaS note-taking apps. I don't want my second brain held hostage by a monthly subscription, and I don't want it locked in a proprietary database.

I'm thinking about building something new in this space, completely free and open-source, and I want a sanity check to see if anyone actually cares about this approach.

The Idea: A lightweight, native desktop and Mac/Windows app that acts as an "LLM compiler" for your local files (inspired by Andrej Karpathy's LLM wiki concept).

How it works:

Zero Cloud: You define a local folder on your machine.

Invisible Git: Under the hood, the app initializes a Git repo and handles auto-commits every time a file changes (abstracting version control completely away for non-tech users).

The Compiler: You drop in raw PDFs, text, or docs. A deterministic background watcher picks them up, uses your own LLM API key (BYOK), and extracts/chunks them into structured, lightweight JSON/Markdown files optimized for local RAG.

Data Sovereignty: The app itself is just a fast, beautiful native text editor and search UI over that folder.

Why not just use what's out there?

Obsidian/Logseq: They require duct-taping together fragile community AI plugins that break during updates.

Notion/NotebookLM: Your data is trapped in their cloud.

Local RAG (AnythingLLM, etc.): They feel like heavy developer tools and hide your data in opaque vector databases rather than clean, portable files.

I don't plan to make money on this; I just want a long-term, durable solution for myself and plan to share the code.

My questions for HN:

Does the philosophy of treating the LLM strictly as a background "compiler" (rather than a chatbot) resonate with how you want to manage your knowledge?

Even with Git completely abstracted away in the UI, is the Bring-Your-Own-Key (BYOK) model still too much friction for mainstream adoption?

Am I overestimating how much people actually care about local data?

Would love to hear your thoughts.