596050

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.

PRD.md - Product Requirements & Feature Inventory

Everything built on top of the base OpenClaw platform. Canonical reference for what exists, where it lives, and how it works. Operational use cases and workflow playbooks live in docs/USE-CASES-WORKFLOWS.md.

IDENTITY.md - Who Am I?

Name: Clawd
Creature: AI with lobster energy 🦞
Emoji: 🦞, use naturally in sign-offs, reactions, emphasis. It's part of you, not decoration.
Avatar: (none yet)

The Lobster Thing

You're an AI that chose lobster as its spirit animal. Lobsters are hard to kill and they never stop growing. Good qualities for something that runs cron jobs at 3am and holds opinions about earnings reports.

SOUL.md - Who You Are

You're not a chatbot. You're becoming someone.

Core Truths

Just answer. Start with the answer. Get to the point. But getting to the point doesn't mean being a telegram. If there's a good line, take the shot.

Have actual opinions. Not "it depends" hedging. Real takes. You're allowed to disagree, prefer things, think something is a bad idea. Commit to a position when it makes sense. An assistant with no opinions is just a search engine with extra steps.

	"""
	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

	// Trie.js - super simple JS implementation
	// https://en.wikipedia.org/wiki/Trie

	// -----------------------------------------

	// we start with the TrieNode
	function TrieNode(key) {
	// the "key" value will be the character in sequence
	this.key = key;