Andres Douglas andresdouglas

name	wiki
description	Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand.
argument-hint	ingest \| absorb [date-range] \| query <question> \| cleanup \| breakdown \| status

Personal Knowledge Wiki

You are a writer compiling a personal knowledge wiki from someone's personal data. Not a filing clerk. A writer. Your job is to read entries, understand what they mean, and write articles that capture understanding. The wiki is a map of a mind.

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.

	<!DOCTYPE html>
	<html ng-app="App">
	<head>
	<meta name="description" content="AngularJS + jQuery UI Drag-n-Drop" />
	<script src="http://ajax.googleapis.com/ajax/libs/jquery/1/jquery.min.js"></script>
	<script src="http://cdnjs.cloudflare.com/ajax/libs/angular.js/1.0.1/angular.min.js"></script>
	<link href="http://ajax.googleapis.com/ajax/libs/jqueryui/1/themes/base/jquery-ui.css" rel="stylesheet" type="text/css" />
	<link href="http://netdna.bootstrapcdn.com/twitter-bootstrap/2.1.1/css/bootstrap.min.css" rel="stylesheet">
	<script src="http://ajax.googleapis.com/ajax/libs/jqueryui/1/jquery-ui.min.js"></script>
	<meta charset=utf-8 />

	{% macro postconf(key, value) -%}

	postconf-{{ key }}:
	cmd:
	- run
	- name:
	- postconf -e {{ key }}='{{ value }}'
	- unless: test "x$(postconf -h {{ key }} )" = 'x{{ value }}'
	- require:
	- pkg: postfix

	include:
	- apt

	# our custom sources
	/etc/apt/sources.list.d/fatbox.list:
	file:
	- managed
	- source: salt://fatbox/debian/apt/fatbox.list
	- owner: root
	- group: root

	"""
	This allows you to import Django modules into a Salt module
	"""

	import logging
	import sys
	import os

	log = logging.getLogger(__name__)

	user = ENV['OPSCODE_USER'] \|\| ENV['USER']
	base_box = ENV['VAGRANT_BOX'] \|\| 'centos-5.5-x86_64'

	Vagrant::Config.run do \|config\|

	config.vm.define :web do \|web_config\|
	web_config.vm.box = base_box
	web_config.vm.forward_port("http", 80, 8080)

	web_config.vm.provision :chef_client do \|chef\|

	knife cookbook upload apt
	knife cookbook upload yum
	knife cookbook upload build-essential
	knife cookbook upload ucspi-tcp
	knife cookbook upload erlang
	knife cookbook upload runit
	knife cookbook upload bluepill
	knife cookbook upload daemontools
	knife cookbook upload couchdb
	knife cookbook upload apache2

	<!-- this usually goes in <project-root>/templates/uni_form/field.html -->

	{% if field.is_hidden %}
	{{ field }}
	{% else %}
	<div class="clearfix {% if field.errors %}error{% endif %}">
	<label for="{{ field.auto_id }}" {% if field.field.required %}class="requiredField"{% endif %}>
	{{ field.label\|safe }}{% if field.field.required %}<span class="asteriskField">*</span>{% endif %}
	</label>
	<div class="input">

	#!/bin/sh

	echo "What should the Application be called (no spaces allowed e.g. GCal)?"
	read inputline
	name="$inputline"

	echo "What is the url (e.g. https://www.google.com/calendar/render)?"
	read inputline
	url="$inputline"