Doug Bryant netinlet

LLM Wiki v2

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.

What the original gets right

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.

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.

Resume Tips

Resumes between 475-600 words have a higher interview rate with a sharp cliff on either end. -- Try to fit it all on one page, 2 pages max.

Have enough keywords to match ~50% of the job requirements, but don't overdo it.

No Objective Section (Unless you're wanting it to take place of a cover letter)

Every 3 sentences, use at least 1 number to demonstrate concrete impact Hovering around 20% of the content having numbers

Arel Cheatsheet on Steroids

A (more) complete cheatsheet for Arel, including NamedFunction functions, raw SQL and window functions.

Tables

posts = Arel::Table.new(:posts)
posts = Post.arel_table # ActiveRecord

Table alias

TL;DR

Install Postgres 9.6, and then:

sudo pg_dropcluster 9.6 main --stop
sudo pg_upgradecluster 9.5 main
sudo pg_dropcluster 9.5 main

Docker - How to cleanup (unused) resources

Once in a while, you may need to cleanup resources (containers, volumes, images, networks) ...

delete volumes

// see: https://github.com/chadoe/docker-cleanup-volumes

$ docker volume rm $(docker volume ls -qf dangling=true)

$ docker volume ls -qf dangling=true | xargs -r docker volume rm

	import { mapState } from 'vuex'

	export default function mapStatesTwoWay (namespace, states, updateCb) {
	const mappedStates = mapState(namespace, states)
	const res = {}
	for (const key in mappedStates) {
	res[key] = {
	set (value) {
	updateCb.call(this, { [key]: value })
	},

	AWSTemplateFormatVersion: '2010-09-09'
	Description: Cognito Stack
	Parameters:
	AuthName:
	Type: String
	Description: Unique Auth Name for Cognito Resources

	Resources:
	# Creates a role that allows Cognito to send SNS messages
	SNSRole:

	{
	"Version": "2012-10-17",
	"Statement": [
	{
	"Effect": "Allow",
	"Action": [
	"cloudformation:CreateStack",
	"cloudformation:UpdateStack",
	"cloudformation:DescribeStacks",
	"cloudformation:ListStacks",

	{
	"Version": "2012-10-17",
	"Statement": [
	{
	"Effect": "Allow",
	"Action": [
	"cloudformation:CreateStack",
	"cloudformation:UpdateStack",
	"cloudformation:DescribeStacks",
	"cloudformation:ListStacks",