Ed Davison ebdavison

See more of my writing here.

In this post, I'll start from scratch and build up to OpenClaw's architecture step by step, showing how you could have invented it yourself from first principles, using nothing but a messaging API, an LLM, and the desire to make AI actually useful outside the chat window.

End goal: understand how persistent AI assistants work, so you can build your own (or become an OpenClaw power user).

First, let's establish the problem

When you use ChatGPT or Claude in a browser, there are several limitations:

Automate LetsEncrypt certificate deployment in SecurityOnion

Prerequisites

A domain name
A DNS provider that works with Certbot. I'm using Cloudflare.
An API token for the DNS provider that is scoped to allow TXT record creation.
SecurityOnion 2.4 with sudo privileges and SSH access.

Turn on user certs in Security Onion (do this only once)

Administration -> Configuration
Options -> Show all configurable settings, including advanced settings

Stream Mastodon activity into a SQLite database

This script subscribes to the live HTTP feed of public activity on my Mastodon instance and writes the results into SQLite database tables.

It needs sqlite-utils and httpx:

pip install sqlite-utils httpx

Then run:

Running Hashcat on Google Cloud's GPU-based VMs

In February 2017, Google announced the availability GPU-based VMs. I spun up a few of these instances, and ran some benchmarks. Along the way, I wrote down the steps taken to provision these VM instances, and install relevant drivers.

Update April 2019: Updated instructions to use instances with the Tesla T4 GPUs.

	javascript: Promise.all([import('https://unpkg.com/turndown@6.0.0?module'), import('https://unpkg.com/@tehshrike/readability@0.2.0'), ]).then(async ([{
	default: Turndown
	}, {
	default: Readability
	}]) => {

	/* Optional vault name */
	const vault = "";

	/* Optional folder name such as "Clippings/" */

	# Initial Setup
	#
	# NOTE: SETUP FOR DEMONSTRATION PURPOSES ONLY, NOT FOR PRODUCTION USE
	#
	# ELASTICSEARCH
	#
	# 1. Download Elasticsearch 6.6 (and unzip)
	# 2. Start two instances of Elasticsearch, each with a different cluster name, port, and data path:
	# ./bin/elasticsearch -E cluster.name=cluster1 -E http.port=9200 -E path.data=./cluster1-data
	# ./bin/elasticsearch -E cluster.name=cluster2 -E http.port=9201 -E path.data=./cluster2-data

	#!/usr/bin/env python3

	'''
	A script to recursively compare two directories (including file size and file hash changes)
	Usage: python3 compare_dirs.py DIR1 DIR2
	'''

	import os, sys, hashlib, unicodedata

	COMPARE_FILES = True # should file sizes be compared if their names are the same?

	#!/usr/bin/env python
	# -- coding: utf-8 --
	# Written as part of https://www.scrapehero.com/how-to-scrape-amazon-product-reviews-using-python/
	from lxml import html
	from json import dump,loads
	from requests import get
	import json
	from re import sub
	from dateutil import parser as dateparser
	from time import sleep

	library(tidycensus)
	library(leaflet)
	library(sf)
	library(viridis)
	options(tigris_use_cache = TRUE)

	il1 <- get_acs(geography = "county",
	variables = c(hhincome = "B19013_001"),
	state = "IL",
	geometry = TRUE) %>%

	# https://webtransparency.cs.princeton.edu/no_boundaries/autofill_sites.html
	# The following is the list of sites from Alexa top 1 million which embed scripts that extract email addresses from the browsers'
	# built-in login (password) managers.
	1000sunny.net
	1001trucscoolsafaire.fr
	123boutchou.com
	12zawodnik.pl
	1pic1day.com
	2012un-nouveau-paradigme.com
	247nigerianewsupdate.co