Memos by Brian Swichkow

• OpenClaw

  OpenClaw is an open-source personal AI assistant platform that runs as a local agent on a user's own hardware, executing tasks autonomously across messaging channels and the local system. Originally...

• Human-AI Augmentation

  Human-AI augmentation is the practice of designing systems where a human and an Artificial Intelligence operate as a unified intelligence — not as tool and user, but as collaborators with distinct...

• How I Replaced My Morning News Routine with AI

  How I replaced my morning news routine with AI is the origin story of BrianBot Broadcast — a daily AI-generated podcast that synthesizes industry news through a curated worldview, published...

• Building with Claude Code as a Non-Engineer

  Building with Claude Code as a non-engineer is the practice of using Claude Code's agentic capabilities to design, build, and ship production software without a traditional engineering background....

• Hermes Glossary

  The Hermes Glossary is a collection of terms used in Hermes Agent, Nous Research's open-source self-improving autonomous agent — spanning its runtime architecture, learning loop, skills system,...

• The Facebook Ads Prank to 57 Agents

  The arc from the Facebook Ads Prank to 57 agents is the story of how Brian Swichkow went from growth hacker to systems architect to augmentation practitioner — and why the same instincts that made a...

• Nous Research

  Nous Research is a decentralized, open-source AI lab, as Fortune described it in April 2025, that trains language models, builds agents and develops training infrastructure, and the creator of Hermes...

• /compress

  The /compress slash command in Hermes Agent manually compresses conversation context by summarizing it, optionally keeping the most recent exchanges verbatim or narrowing the summary to a focus...

• claw migrate

  hermes claw migrate is the older spelling of hermes import-agent openclaw, the Hermes Agent command that imports an OpenClaw setup's persona, memory, skills and configuration into Hermes. The command...

• Hermes Slash Command

  A Hermes Slash Command is a /-prefixed instruction typed into Hermes Agent, either a built-in command or an installed skill, dispatched in the interactive CLI and on connected messaging platforms....

• /steer

  The /steer slash command in Hermes Agent injects a mid-run note that the running agent receives after its next tool call, without interrupting the turn or starting a new user turn. Per the Hermes...

• Hermes Terminal UI

  Hermes Terminal UI is a feature of Hermes Agent that provides its modern terminal front-end, backed by the same Python runtime as the classic CLI and sharing its agent, sessions and slash commands....

• Nous Portal

  Nous Portal is Nous Research's unified subscription gateway, a single account that supplies Hermes Agent with model inference and hosted tools, and the docs' recommended way to run the agent. The...

• Hermes Container Hardening

  Hermes Container Hardening is the set of Docker security flags and resource limits that Hermes Agent applies to every container when terminal commands run on the docker backend. Container isolation...

• MCP for Personal Knowledge Systems

  MCP for personal knowledge systems is the practice of using the Model Context Protocol to connect a personal knowledge base — notes, memos, documents, research — to AI models as persistent,...

• The Augmentation Stack

  The Augmentation Stack is a four-layer architecture — Memory → Mind → Mouth → Myth — for building human-AI augmentation systems that compound over time rather than resetting with each interaction....

• AI Memory Systems

  AI memory systems are the tools and architectures that give Artificial Intelligence models persistent context across sessions — the ability to remember who you are, what you've worked on, and what...

• Multi-Agent Orchestration at Scale

  Multi-agent orchestration at scale is the practice of coordinating dozens of specialized AI agents into a coherent system that operates autonomously, shares context, and produces compounding output —...

• Model Context Protocol (MCP)

  Model Context Protocol (MCP) is an open protocol developed by Anthropic that standardizes how Artificial Intelligence models connect to external tools, data sources, and systems. Anthropic introduced...

• CLAUDE.md as Infrastructure

  CLAUDE.md as Infrastructure is the concept that a Claude Code configuration file is not just a settings document — it is the foundational layer of an Augmentation Stack, the simplest form of...