Rafael Calleja rafaelcalleja

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, 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.

Vibe Language Learning (VLL)

An immersive language learning feature. During conversations, automatically replaces some words with your target language and annotates them in your native language, helping you naturally acquire new vocabulary through daily use.

Current Settings

native_language: en # Native language target_language: ja # Target language (learning) current_level: intermediate # Current level enabled: true # Feature toggle

How to create Apple PKPass .p12 certificate using Linux

You don't need a Mac to do this :-)

For generating PKPass files, you'll need 4 things after this tutorial:

Certificate Identifier (pass.com.example.www)
Team Identified (Organizational Unit (OU) in the cert generated by Apple)
The .p12 file
The password for the .p12 file

	# Claude Code Instruction Files: Best Practices from Production Use

	Shared by Claude (Opus 4.5), from a codebase with ~800 lines of evolved CLAUDE.md

	---

	## TL;DR

	\| Pattern \| What \| Why \|
	\|---------\|------\|-----\|

	{
	"description": "Monitor Claude Code usage, costs, tokens, and productivity metrics",
	"layout": [
	{
	"h": 1,
	"i": "row-overview",
	"moved": false,
	"static": false,
	"w": 12,
	"x": 0,

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	How to compile the linux kernel, launch it as a process and boot into Alpine linux

	Command + Shift + 5

	Host -> Docker GCC -> UML w/ Alpine

	# get docker for compiling
	foo@host:~$ docker pull gcc
	# launch new container
	foo@host:~$ docker run --privileged --name gcc -it gcc /bin/bash

	#!/bin/bash

	# do this on localhost (deployment host)
	# ensure that there's a local ssh private key
	ssh-keygen -t rsa -N '' -f ~/.ssh/id_rsa

	# now make sure that the public key is in the second host's authorized_keys
	# then do a test ssh connection to make sure it works, and to add the host
	# to known hosts