Skip to content

Instantly share code, notes, and snippets.

View ahhh's full-sized avatar
👾
danger code

Dan Borges ahhh

👾
danger code
View GitHub Profile

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.

@karpathy
karpathy / microgpt.py
Last active November 9, 2026 12:39
microgpt
"""
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
@aphix
aphix / BetterAirlineClub.userscript.js
Last active October 15, 2026 13:46
[1.4.0] Better Airline Club + Cost Per PAX Combined & Improved
// ==UserScript==
// @name Better Airline Club + Cost Per PAX Combined & Improved
// @namespace http://tampermonkey.net/
// @version 1.4.0
// @description Enhances airline-club.com and v2.airline-club.com airline management game
// @author Aphix/Torus (original "Cost Per PAX" portion by Alrianne @ https://github.com/wolfnether/Airline_Club_Mod/)
// @match https://*.airline-club.com/
// @icon https://www.google.com/s2/favicons?domain=airline-club.com
// @downloadURL https://gist.githubusercontent.com/aphix/fdeeefbc4bef1ec580d72639bbc05f2d/raw/BetterAirlineClub.userscript.js
// @updateURL https://gist.githubusercontent.com/aphix/fdeeefbc4bef1ec580d72639bbc05f2d/raw/BetterAirlineClub.userscript.js
@ropnop
ropnop / go-sharp-loader.go
Created August 5, 2020 17:12
Example Go file embedding multiple .NET executables
package main
/*
Example Go program with multiple .NET Binaries embedded
This requires packr (https://github.com/gobuffalo/packr) and the utility. Install with:
$ go get -u github.com/gobuffalo/packr/packr
Place all your EXEs are in a "binaries" folder
@rossja
rossja / ECB Cryptolocker.md
Last active February 25, 2020 23:04
ECB CryptoLocker

ECB CryptoLocker Idea

Random musings from a 3 AM brain spin. Likely a very stupid idea :)

To Lock

  • create a list of files to lock
  • randomize the list order
  • generate a random 8 bit ascii hex string to use as an IV
@williballenthin
williballenthin / macOS_savedstate.py
Last active April 8, 2026 04:26
parse macOS savedState files
'''
parse SavedState artifacts extracted from OSX.
author: Willi Ballenthin (william.ballenthin@fireeye.com)
license: Apache 2.0
'''
import re
import sys
import json
import struct
#!/usr/bin/env python2.7
import argparse
import binascii
import sys
import base64
import hashlib
from Crypto.Cipher import AES
from pkcs7 import PKCS7Encoder
import random
from random import randint
@williballenthin
williballenthin / macOS_keychain.py
Last active February 7, 2025 10:37
bling.py - extract keys from macOS keychains.
#!/usr/bin/env python3
'''
bling.py - extract keys from macOS keychains.
installation:
pip install pytz hexdump vivisect-vstruct-wb tabulate argparse pycryptodome
usage:
python bling.py /path/to/keychain-db <password> ./path/to/output/directory
@wybiral
wybiral / noscript-tracking.go
Last active October 28, 2024 23:01
Tracking cursor position in real-time with remote monitoring (without JavaScript)
// Tracking cursor position in real-time without JavaScript
// Demo: https://twitter.com/davywtf/status/1124146339259002881
package main
import (
"fmt"
"net/http"
"strings"
)
@williballenthin
williballenthin / macOS_stickies.py
Last active June 24, 2022 15:32
extract entries from the osx sticky database
'''
parse osx sticky databases.
author: Willi Ballenthin <william.ballenthin@fireeye.com>
license: Apache 2.0
usage:
$ python extract_stickies.py /path/to/input.bin /path/to/output/directory/
'''