Zitao Xiong caoer

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.

Better local require() paths for Node.js

Problem

When the directory structure of your Node.js application (not library!) has some depth, you end up with a lot of annoying relative paths in your require calls like:

var Article = require('../../../models/article');

Those suck for maintenance and they're ugly.

Possible solutions

Smiley Face

Project Title

One Paragraph of project description goes here

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

	## General info:
	# Function starts with @
	# Variable starts with $
	# Return of the most recently run function made by $@
	# Key comments marked with ##

	## Version of IV must be set first
	~version: "2.1"

	# Telegram doesn't support JW Player which is used in videoheaders

	-- show running queries (pre 9.2)
	SELECT procpid, age(clock_timestamp(), query_start), usename, current_query
	FROM pg_stat_activity
	WHERE current_query != '<IDLE>' AND current_query NOT ILIKE '%pg_stat_activity%'
	ORDER BY query_start desc;

	-- show running queries (9.2)
	SELECT pid, age(clock_timestamp(), query_start), usename, query
	FROM pg_stat_activity
	WHERE query != '<IDLE>' AND query NOT ILIKE '%pg_stat_activity%'

	[Unit]
	Description=AutoSSH reverse tunnel service for jump.you.io 100022 -> 22
	After=network.target

	[Service]
	Environment="AUTOSSH_GATETIME=0"
	ExecStart=/usr/bin/autossh -M 0 -o "ExitOnForwardFailure=yes" -o "ServerAliveInterval 30" -o "ServerAliveCountMax 3" -NR 10022:127.0.0.1:22 user@jump.you.io -i /home/root/.ssh/id_rsa

	[Install]
	WantedBy=multi-user.target

	mr Marathi
	bs Bosnian
	ee_TG Ewe (Togo)
	ms Malay
	kam_KE Kamba (Kenya)
	mt Maltese
	ha Hausa
	es_HN Spanish (Honduras)
	ml_IN Malayalam (India)
	ro_MD Romanian (Moldova)

	" copy all this into a vim buffer, save it, then...
	" source the file by typing :so %
	" Now the vim buffer acts like a specialized application for mastering vim

	" There are two queues, Study and Known. Depending how confident you feel
	" about the item you are currently learning, you can move it down several
	" positions, all the way to the end of the Study queue, or to the Known
	" queue.

	" type ,, (that's comma comma)

	// Use Gists to store code you would like to remember later on
	console.log(window); // log the "window" object to the console