Scott J. Walter ScottJWalter

Deploying Hermes Agent on Dokploy

A step-by-step guide to deploying NousResearch Hermes Agent on a VPS using Dokploy, secured with Tailscale and a locked-down firewall.

Prerequisites

A VPS with Dokploy installed
Dokploy API token (Settings → API Keys in Dokploy UI)
A Telegram bot token from @BotFather
An LLM API key (OpenAI-compatible endpoint)

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.

image-paths are obviously broken on this one, you can replace the links with images of your own.

[!fig|left|snail]- ![[snail.png|Snail Facts!|200]] Snails are cool! Click to learn more!

Snails r cute :3

They be eating leaf

Swirly soft-boi chomkers :3333

Read-more [[Le Smail Manifesto|here]]!

[!fig|right|px] ![[meloonics_64.png|64]] It me!

ZSH on Termux!

Spice up termux with beautiful themes and productivity plugins to make your life easier!

Install ZSH, GIT & LSD

pkg install zsh git lsd vim

	using BioStructures
	using LinearAlgebra
	using PlotlyJS
	using DataFrames
	using StaticArrays
	using Rotations
	using ImageTransformations
	using CoordinateTransformations
	using Interpolations
	using FFTW

	# -----------------------------------------------------------------------------
	# AI-powered Git Commit Function
	# Copy paste this gist into your ~/.bashrc or ~/.zshrc to gain the `gcm` command. It:
	# 1) gets the current staged changed diff
	# 2) sends them to an LLM to write the git commit message
	# 3) allows you to easily accept, edit, regenerate, cancel
	# But - just read and edit the code however you like
	# the `llm` CLI util is awesome, can get it here: https://llm.datasette.io/en/stable/

	gcm() {

	\[[+Home]] %% tags:: #MOC %%
	# Physical Objects MOC

	```meta-bind-button
	label: New Physical Object
	hidden: false
	class: ""
	tooltip: ""
	id: ""
	style: primary

	---
	Purchased: <% tp.date.now("YYYY-MM-DD") %>
	Price:
	URL:
	---
	tags:: [[🛍️ Physical Objects MOC]]
	<% await tp.file.move("/Spaces/Physical Objects/" + tp.date.now("YYYY-MM-DD") + " " + tp.file.title) %>
	# [[<% tp.date.now("YYYY-MM-DD") + " " + tp.file.title %>]]

	# Specs

	; ---------------------------------------------------------------------------------------------------------------------
	; Ctrl+Alt+SPECIAL+K --> Toggle Audio
	;
	^!#k:: SoundSetMute !SoundGetMute()

	; ---------------------------------------------------------------------------------------------------------------------
	; Ctrl+Alt+Shift+SPECIAL+K --> Turn Audio OFF
	;
	^!+#K:: SoundSetMute true

	; ---------------------------------------------------------------------------------------------------------------------
	; Ctrl+Alt+SPECIAL+M --> Toggle Microphone
	;
	^!#m:: SoundSetMute !SoundGetMute(, "Microphone"),, "Microphone"

	; ---------------------------------------------------------------------------------------------------------------------
	; Ctrl+Alt+Shift+SPECIAL+M --> Turn Microphone OFF
	;
	^!+#M:: SoundSetMute true,, "Microphone"