Tony Li atom2ueki

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.

name	orchestrating-swarms
description	Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

Release workflows

Branch types

Concatenate multiple VOB into same

ffmpeg -i "concat:/Path/File1.VOB|/Path/File2.VOB" -c copy file_output.vob

Convert VOB video to x256

ffmpeg -i file_input.vob -vf yadif -c:v libx265 -preset slow -crf 20 -c:a aac -b:a 256k file_output.mkv

Cropping a video

Parse Cloud Module for managing Facebook Login server side using Express.

To log in, visit https://YOUR_SUBDOMAIN.parseapp.com/login.

Installation

Move main.js and app.js into your cloud/ folder in Cloud Code if it's a new project. If you're already using Express, update your app.js accordingly.

If you already have a Parse Hosting app set up, but you're not using Express yet, add the following to your `main.js:

	"""
	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

	/**
	* Sample React Native App
	* https://github.com/facebook/react-native
	*/
	'use strict';

	const React = require('react-native');
	const FBSDKCore = require('react-native-fbsdkcore');
	const FBSDKLogin = require('react-native-fbsdklogin');

	import tensorflow as tf
	import numpy as np
	import time

	N=10000
	K=4
	MAX_ITERS = 1000

	start = time.time()

	class MainApp extends Component {
	constructor(props) {
	super(props);
	}

	renderScene(route, navigator) {
	var Component = route.component;
	return (
	<Component route={route} navigator={navigator} />
	);

	//
	// UITableView+CATransaction.swift
	//
	// Created by Marcel Dierkes on 08.05.15.
	// Copyright (c) 2015 Marcel Dierkes. All rights reserved.
	//

	import UIKit
	import QuartzCore