Skip to content

Instantly share code, notes, and snippets.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

@davatron5000
davatron5000 / gist:2254924
Created March 30, 2012 20:57
Static Site Generators

Backstory: I decided to crowdsource static site generator recommendations, so the following are actual real world suggested-to-me results. I then took those and sorted them by language/server and, just for a decent relative metric, their Github Watcher count. If you want a heap of other projects (including other languages like Haskell and Python) Nanoc has the mother of all site generator lists. If you recommend another one, by all means add a comment.

Ruby