Discover gists

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.

const addBookmarkBtn = document.getElementById("add-bookmark");
const bookmarkList = document.getElementById("bookmark-list");
const bookmarkNameInput = document.getElementById("bookmark-name");
const bookmarkUrlInput = document.getElementById("bookmark-url");

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.

NaiveProxy: Ультимативный гайд по настройке (2026)

📺 Видео-версия гайда

Инструкции по установке

1. Подключаемся к серверу:

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	#!/usr/bin/env bash
	#
	# Simple Intel x520 EEPROM patcher
	# Modifies the EEPROM to unlock the card for non-intel branded SFP modules.
	#
	# Copyright 2024 Ivan Vatlin <me@jeffangelion.ru>
	#
	# Licensed under the GPLv3
	#
	# Based on research described at https://forums.servethehome.com/index.php?threads/patching-intel-x520-eeprom-to-unlock-all-sfp-transceivers.24634/

	#!/usr/bin/env bash

	# VMware Fusion Latest Version Downloader, Installer, and Updater
	# This script automatically finds, downloads, and optionally installs the highest version available
	#
	# Inspired by this gist: https://gist.github.com/jetfir3/6b28fd279bbcadbae70980bd711a844f
	#
	# Usage: $0 [-y] [-i] [-d] [-f] [-t <dmg_path>]
	# -y: Skip download confirmation prompt
	# -i: Automatically install after download (implies -y)