karpathy

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.

POWERFULMOVES

Claude Agent SDK Technical Specification

Version: 1.0.0 Protocol Version: 2024-11-05 Last Updated: 2026-01-10

Table of Contents

1. Overview
2. Architecture

wong2

Task

Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, exit_plan_mode, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.

When to use the Agent tool:

• If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended

When NOT to use the Agent tool:

• If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
• If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
• If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly

evdcush

#!/usr/bin/env bash

# This script comes from Joplin, MIT License Copyright Laurent Cozic:
# https://github.com/laurent22/joplin/blob/dev/Joplin_install_and_update.sh
# Modified here by github.com/evdcush to instead install and update Logseq.

set -e

trap 'handleError' ERR

cherti

#!/bin/bash

name=$RANDOM
url='http://localhost:9093/api/v1/alerts'

echo "firing up alert $name" 

# change url o
curl -XPOST $url -d "[{ 
	\"status\": \"firing\",

justincjahn

#
# INPUT - Logstash listens on port 8514 for these logs.
#

input {
  udp {
    port => "8514"
    type => "syslog-cisco"
  }
  

zchee

--- Actions ---
$Copy                                              <M-C>
$Cut                                               <M-X> <S-Del>
$Delete                                            <Del> <BS> <M-BS>
$LRU                                              
$Paste                                             <M-V>
$Redo                                              <M-S-Z> <A-S-BS>
$SearchWeb                                         <A-S-G>
$SelectAll                                         <M-A>
$Undo                                              <M-Z>