rohitg00

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.

r4sky0

#!/bin/bash
#
# Restart Bluetooth Module on Mac OS X
#
# Requires Blueutil to be installed: http://brewformulas.org/blueutil

BT="/usr/local/bin/blueutil"

log() {
	echo "$@"

jabney

// entropy.js MIT License © 2014 James Abney http://github.com/jabney

/***************************************
 * ES2015
 ***************************************/

// Shannon entropy in bits per symbol.
function entropy(str) {
  const len = str.length
 

ryanray

# config/deploy.rb

# probably a lot of ways to improve this...
set :application, 'my_app'
set :repo_url, 'git@github.com:USERNAME/my_app.git'
# should set up a deploy user
set :user, 'deploy'

set :deploy_to, '/var/www/my_app'
set :scm, :git

jdhenke

#!/usr/bin/python
'''
MARKOV MODEL MASHUPS

Creates 'lyrical mashups' using Markov Models.
Can use characters or words as state. (You should add more mediums!)

Example files used:
    mashup.py       # this script
    sonnets.txt     # all of shakespeare's sonnets