LLM-Wiki is a trap. It promises "near zero maintenance" but delivers markdown files with no foreign keys, no permissions, no schema, and a "small enough" disclaimer that admits it doesn't scale. The sheep follow. The rest of us laugh. 🐑💀
A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 20K+ Stars ⭐️, a persistent memory engine for AI coding agents.
This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.
The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.
All credit to this thread for figuring out how to do this, I'm just documenting it more thoroughly.
Tested on Nova Air C with firmware 3.5 (2023-11-20).
Handwriting optimisation makes the pen usable in apps installed from the play store. By default it's only available for OneNote, Evernote and WPS -- they have a 'handwriting' tab in the optimisation settings, other apps don't -- but can be enabled for any app by editing the file /onyxconfig/eac_config as root.
Note: whenever you edit eac_config, you have to reboot the device for the changes to take effect. Just restarting the app isn't enough.