Skip to content

Instantly share code, notes, and snippets.

@qoomon
qoomon / conventional-commits-cheatsheet.md
Last active April 18, 2026 11:30
Conventional Commits Cheatsheet

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.

@rohitg00
rohitg00 / llm-wiki.md
Last active April 18, 2026 11:29 — forked from karpathy/llm-wiki.md
LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory

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.

@l6-ParsonsMatthew-37
l6-ParsonsMatthew-37 / Casino Bonus.md
Created April 18, 2026 06:14
Crypto Rewards & Welcome Bonus Guide 2026 Digital Promotions, Deposit Rewards & New User Offers

Crypto Rewards & Welcome Bonus Guide 2026 Digital Promotions, Deposit Rewards & New User Offers

The digital asset ecosystem continues to evolve rapidly, and with it comes a new generation of crypto reward platforms designed to provide incentives, welcome bonuses, and promotional benefits for new and active users.

This comprehensive guide explains how modern crypto reward programs work, how to activate your welcome reward, and how to maximize long-term benefits through ongoing promotions and deposit incentives.

👉 Start your welcome reward: WINASPIN CASINO


<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>By The Sea — Your Sailing Session Companion</title>
<meta name="description" content="By The Sea is the ultimate iOS app for sailors and foilers. Track sessions, analyze speed, predict conditions, and sail smarter.">
<style>
:root {
--ocean-deep: #0a1f3d;
@marcoarment
marcoarment / parallelize.c
Last active April 18, 2026 11:21
A simple shell command parallelizer.
/* parallelize: reads commands from stdin and executes them in parallel.
The sole argument is the number of simultaneous processes (optional) to
run. If omitted, the number of logical CPUs available will be used.
Build: gcc -pthread parallelize.c -o parallelize
Demo: (for i in {1..10}; do echo "echo $i ; sleep 5" ; done ) | ./parallelize
By Marco Arment, released into the public domain with no guarantees.