Bilgehan Zeki ÖZAYTAÇ WildGenie

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.

🧠 Ultimate LLM Codebase Brain Dump Prompt

This prompt is designed for GPT-5, Claude Opus 4.1, Cursor, Claude Code, and cursor-agent to perform a deep, structured analysis of any codebase without pasting the entire repo into chat.

It guides the LLM to:

Browse and discover the codebase using built-in repo tools
Read only the necessary files in intelligent order
Analyze the system at high, mid, and low levels
Identify features, their business purposes, how they work, and how they interact
Output a complete master knowledge document inside codebase-analysis-docs/

Domain Aggregates

Bill

class Bill
{
    // TODO: Add methods
}

Flutter Oxford5000

CI/CD

Fabric EComm Project

TARGET

{
  getProductDetails(input: { sku: "FUR_BED_02" }) {
    itemId
    categories {
      id

	# tutorial video link : https://youtu.be/dYt9xJ7dnpU
	# colab link : https://colab.research.google.com/drive/1xSbu-b-EwYd6GdaFPRVgvXBX_mciZ41e?usp=sharing
	# repo link : https://github.com/ai-forever/Kandinsky-2
	# used repo commit hash : a4354c04d5fbd48851866ef7d84ec444d3d50102

	# those who getting cuda error
	# pip uninstall torch
	# pip3 install torch==1.13.1 torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117

	import os

	# launch your own Gradio Web Demo of Arcane style transfer by following the steps below
	# open a jupyter notebook, code editor (vs code etc), or google colab
	# pip install gradio
	# copy the code below into a file or cell in a python notebook and run it
	# that's it, a web demo will appear in your python notebook or web browser
	# github: https://github.com/jjeamin/anime_style_transfer_pytorch
	# HF blog: https://huggingface.co/blog/gradio-spaces

	import gradio as gr



	# DD Windows Server 2008 R2 64位精简版 [账户Administrator密码nat.ee]
	wget --no-check-certificate -qO InstallNET.sh 'https://moeclub.org/attachment/LinuxShell/InstallNET.sh' && bash InstallNET.sh -dd 'https://oss.sunpma.com/Windows/Win_Server2008R2_sp1_64_Administrator_nat.ee.gz'

	# DD Windows Server 2012 R2 64位精简版 [账户Administrator密码nat.ee]
	wget --no-check-certificate -qO InstallNET.sh 'https://moeclub.org/attachment/LinuxShell/InstallNET.sh' && bash InstallNET.sh -dd 'https://oss.sunpma.com/Windows/Win_Server2012R2_64_Administrator_nat.ee.gz'

	# DD Windows Server 2016 64位精简版 [账户Administrator密码nat.ee]
	wget --no-check-certificate -qO InstallNET.sh 'https://moeclub.org/attachment/LinuxShell/InstallNET.sh' && bash InstallNET.sh -dd 'https://oss.sunpma.com/Windows/Win_Server2016_64_Administrator_nat.ee.gz'