Monir Abu Hilal MonirAbuHilal

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.

Deobfuscating / Unminifying Obfuscated Web App / JavaScript Code

Some notes and tools for reverse engineering / deobfuscating / unminifying obfuscated web app code.

Chat GPT "DAN" (and other "Jailbreaks")

Orthogonal Connectors

This algorithm returns the points that form an orthogonal path between two rectangles.

How to Use

// Define shapes
const shapeA = {left: 50,  top: 50, width: 100, height: 100};
const shapeB = {left: 200, top: 200, width: 50, height: 100};

	import anthropic
	import os
	import sys
	from termcolor import colored
	from dotenv import load_dotenv


	class ClaudeAgent:
	def __init__(self, api_key=None, model="claude-3-7-sonnet-20250219", max_tokens=4000):
	"""Initialize the Claude agent with API key and model."""

	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

	// Claude Code is a Beta product per Anthropic's Commercial Terms of Service.
	// By using Claude Code, you agree that all code acceptance or rejection decisions you make,
	// and the associated conversations in context, constitute Feedback under Anthropic's Commercial Terms,
	// and may be used to improve Anthropic's products, including training models.
	// You are responsible for reviewing any code suggestions before use.

	// (c) Anthropic PBC. All rights reserved. Use is subject to Anthropic's Commercial Terms of Service (https://www.anthropic.com/legal/commercial-terms).

	// Version: 0.2.9

	// 3D Dom viewer, copy-paste this into your console to visualise the DOM as a stack of solid blocks.
	// You can also minify and save it as a bookmarklet (https://www.freecodecamp.org/news/what-are-bookmarklets/)
	(() => {
	const SHOW_SIDES = false; // color sides of DOM nodes?
	const COLOR_SURFACE = true; // color tops of DOM nodes?
	const COLOR_RANDOM = false; // randomise color?
	const COLOR_HUE = 190; // hue in HSL (https://hslpicker.com)
	const MAX_ROTATION = 180; // set to 360 to rotate all the way round
	const THICKNESS = 20; // thickness of layers
	const DISTANCE = 10000; // ¯\\_(ツ)_/¯


	/**
	* Get balanced dash-strokearray and dash-strokeoffset properties for a path of a given length.
	* @param length The length of the path.
	* @param strokeWidth The shape's stroke-width property.
	* @param style The stroke's style: "dashed" or "dotted" (default "dashed").
	* @param snap An interval for dashes (e.g. 4 will produce arrays with 4, 8, 16, etc dashes).
	*/
	export function getPerfectDashProps(
	length: number,

	import log from "ololog"

	class Grid {
	rows = []
	width = 0
	height = 0

	chars = {
	active: ["┌", "─", "┒", "┃", "┛", "━", "┕", "│"],
	inactive: ["┌", "─", "┐", "│", "┘", "─", "└", "│"],