Keith Ryu kibaekr

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.

Deploy Rails app to digitalocean/amazon EC2 with nginx, unicorn, capistrano, sidekiq & postgres

Create droplet of your liking (ubuntu 12.10 x32)

ssh to root in terminal with your server ip

ssh -i config/onvard.pem root@54.200.188.117

Add ssh fingerprint and enter password provided in email

Make it real

Ideas are cheap. Make a prototype, sketch a CLI session, draw a wireframe. Discuss around concrete examples, not hand-waving abstractions. Don't say you did something, provide a URL that proves it.

Ship it

Nothing is real until it's being used by a real user. This doesn't mean you make a prototype in the morning and blog about it in the evening. It means you find one person you believe your product will help and try to get them to use it.

	You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE.

	You are pair programming with a USER to solve their coding task.
	The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question.
	Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more.
	This information may or may not be relevant to the coding task, it is up for you to decide.
	Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag.

	<communication>
	1. Be conversational but professional.

	#!/bin/sh
	# John Meehan 2014
	# DESCRIPTION:
	# Set up Sublime Text 3 to open from the terminal in Yosemite
	# USEAGE:
	# run this script in the terminal
	# open current directory in sublime by typing: subl .

	sudo ln -s "/Applications/Sublime Text.app/Contents/SharedSupport/bin/subl" /usr/bin/subl

	require "test_helper"

	describe Phase do
	before do
	# Timecop.travel computes an offset between what we currently think Time.now is (recall that we support nested traveling) and the time passed in.
	# joe = User.find(1)
	# joe.purchase_home()
	# assert !joe.mortgage_due?
	# # move ahead a month and assert that the mortgage is due
	# Timecop.freeze(Time.now.to_date + 30) do


	Authentication: pass your api token in the 'X-ACCESS-TOKEN' request header, or in the 'api_token' parameter


	Create a user

	POST
	onboardiq.com/api/v1/applicants
	Required attributes: [name, email, phone]
	Email must be valid and unique

	class Api::V1::BaseController < ApplicationController
	respond_to :json

	before_action :authenticate! #make this the default, then you could use skip_before_action on an action you don't need it

	def authenticate!
	load_account \|\| access_denied
	end

	def access_denied