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.