I turned Karpathy's LLM Wiki into a native GNOME app (and it works offline)

Description and use

<p>In April, Andrej Karpathy posted a short "idea file" called <strong>LLM Wiki</strong>. The pitch: stop making your model re-read raw documents on every question. Let it <strong>build and maintain a wiki</strong> from your sources instead, a persistent Markdown knowledge base that gets better every time you add something.</p> <p>The internet went wild. Within a week there were thousands of repos implementing it, and two of them crossed 20,000 GitHub stars.</p> <p>There was one thing missing for me: <strong>none of them felt at home on a Linux desktop.</strong> So we built <strong>gknowledge<

Problem

<p>In April, Andrej Karpathy posted a short "idea file" called <strong>LLM Wiki</strong>. The pitch: stop making your model re-read raw documents on every question. Let it <strong>build and maintain a wiki</strong> from your sources instead, a persistent Markdown knowledge base that gets better every time you add something.</p> <p>The internet went wild. Within a week there were thousands of repos implementing it, and two of them crossed 20,000 GitHub stars.</p> <p>There was one thing missing for me: <strong>none of them felt at home on a Linux desktop.</strong> So we built <strong>gknowledge<

Outcome

<p>In April, Andrej Karpathy posted a short "idea file" called <strong>LLM Wiki</strong>. The pitch: stop making your model re-read raw documents on every question. Let it <strong>build and maintain a wiki</strong> from your sources instead, a persistent Markdown knowledge base that gets better every time you add something.</p> <p>The internet went wild. Within a week there were thousands of repos implementing it, and two of them crossed 20,000 GitHub stars.</p> <p>There was one thing missing for me: <strong>none of them felt at home on a Linux desktop.</strong> So we built <strong>gknowledge<

Evidence

I turned Karpathy's LLM Wiki into a native GNOME app (and it works offline)

Source