Huy's Wiki

Corey Ganim — I Built the ULTIMATE AI Second Brain (Karpathy's LLM Wiki Setup Guide)

Properties1
tagsyoutube, ai, corey-ganim

7 min read

Corey Ganim — I Built the ULTIMATE AI Second Brain (Karpathy’s LLM Wiki Setup Guide)

Source: YouTube Channel: Corey Ganim (17900 subs) Duration: 18:41 Views: 8317 · Likes: 176 Video: Watch on YouTube

🔗 Deploy your own Hermes agent on Hostinger -10% off any plan with code COREY10: http://hostinger.com/corey10 (use code COREY10)

Grab the free step-by-step Hermes Second Brain setup guide here: https://corey-ganim.kit.com/60fc0fe6d9

In this episode I break down exactly how I built the ultimate AI second brain using Hermes and its built-in LLM Wiki skill — the same setup Andrej Karpathy has been talking about for personal knowledge bases. I walk through why Hermes beats Claude Code, OpenClaw, and Obsidian for this use case, the three-layer architecture under the hood (raw sources, the wiki, the schema), and the exact division of labor between you (curating sources) and the agent (summarizing, filing, querying). Then I deploy a fresh Hermes agent on a Hostinger VPS step by step, hook it up to OpenAI Codex and Telegram, and feed it its first source using the MarkDownload Chrome extension. By the end of the episode you will know exactly how to deploy your own self-improving second brain that gets smarter every time you feed it.

Links: Hostinger VPS (Hermes one-click deploy): https://hostinger.com Hermes Agent: https://hermes.example.com MarkDownload Chrome Extension: https://chromewebstore.google.com/detail/markdownload-markdown-web/pcmpcfapbekmbjjkdalcgopdkipoggdi Telegram BotFather: https://t.me/BotFather

Timestamps 00:00 – Intro 00:25 – Why Hermes beats Claude Code and Obsidian for a second brain 00:45 – The division of labor: human curates, agent files 01:20 – Three core operations: ingest, query, lint 02:24 – The three layers of the knowledge base 03:10 – Why you only need Obsidian if you want to read files by hand 03:40 – Hermes’ self-improving learning loop and built-in scheduler 05:30 – Why deploy on a VPS instead of locally 06:15 – Choosing the KVM2 plan and using code COREY10 07:50 – One-click Hermes deploy and setting admin credentials 09:00 – Connecting OpenAI Codex and choosing your default model 09:45 – Setting up Telegram with BotFather 12:20 – Using

Key Insights

You’re in the right place if you’re finally ready to build your AI-powered second brain because in this episode, I’m going to be showing you how to build a compounding knowledge base that actually gets smarter over time. Specifically, I’m going to be showing you how to use an AI agent called Hermes, which is an open-source AI agent, which is kind of like Open Claw but a lot smarter and a lot easier to set up. So, in this video, we are going to be breaking down the why behind using Hermes and not other popular tools like Claude Code, Obsidian, how to quickly and securely set up Hermes with zero code required, how to set up your second brain with Hermes, and then how to test it to make sure it works. So, by the end of this episode, you are going to have a fully functional AI-powered second brain giving you and your business a massive advantage against your competitors. So, let’s get started. So, why are we using Hermes versus a Claude Code or an Obsidian? Those are the two most popular tools that everybody talks about when it comes to building a second brain, and there’s a couple of reasons. So, first and foremost, Hermes has a built-in skill that comes off the shelf called the LLM Wiki skill, which is literally the second brain function built into Hermes. So, let’s talk about what that looks like. So, first and foremost, with this skill, there’s a division of labor between you as the human and the Hermes agent. So, you as the human, your job is to curate the sources. Your job is to go out and find the data and the references that you want inside of your second brain. Now, the Hermes agent’s job is to summarize and file that away for future you. So, what does it look like uh as far as the core operations of the Hermes agent and filing those away? So, the first thing it’s going to do when you give it a new reference file, let’s say we give it a tweet or an article or a website, it’s going to ingest that that document and add it as a source to your wiki. So, it does that automatically based on the built-in skill. The next thing that it’s going to do is when you ask the Hermes agent a specific question, it is going to query your wiki. It’s going to look at anything that you’ve given it as a source, anything that it’s ingested, and give you your answer based on the query that it did to your knowledge base. And then lastly, the third core operation is what’s called lint, which is an audit {slash} health check of the wiki. So, you can run the lint command. Uh best practices to do this once a month. And what that’s going to do is the Hermes agent is going to look at your entire knowledge base, your entire second brain, and it is going to determine do we have any uh sources that are contradictory? Do we have any sources that are more than 90 days old that are likely out of date? Do we have any sources that are too long? If there are sources over, I believe it’s 200 lines or or maybe it’s 200 pages, Hermes will flag that automatically as uh a source that can potentially be split into multiple individual sources, which will make the querying function of those sources a lot more accurate. And then, as far as the three layers of the knowledge base, uh when it looks If you were to look at it under the hood, there’s only three layers, right? So, there’s layer one, which is the raw sources. This is what you as the human are giving it to ingest. So, these files are read-only. The Hermes agent does not touch the raw sources. It simply ingests them, right? The second layer is the actual wiki itself. This is the agent-owned, essentially, web of different markdown files. So, the Hermes agent is going to take the files that it ingests that are sitting in layer one, and then it’s going to organize them into a wiki. So, then layer three is the actual schema, the structure and the tags that the Hermes agent builds out in order to make the querying operation easy and low friction. So, it’s going to apply certain tags, it’s going to create an internal st

Transcript continues…

Chapters

  • 00:00 — Intro
  • 00:25 — Why Hermes beats Claude Code and Obsidian for a second brain
  • 00:45 — The division of labor: human curates, agent files
  • 01:20 — Three core operations: ingest, query, lint
  • 02:24 — The three layers of the knowledge base
  • 03:10 — Why you only need Obsidian if you want to read files by hand
  • 03:40 — Hermes’ self-improving learning loop and built-in scheduler
  • 05:30 — Why deploy on a VPS instead of locally
  • 06:15 — Choosing the KVM2 plan and using code COREY10
  • 07:50 — One-click Hermes deploy and setting admin credentials
  • 09:00 — Connecting OpenAI Codex and choosing your default model
  • 09:45 — Setting up Telegram with BotFather
  • 12:20 — Using MarkDownload to clip sources into Markdown
  • 13:35 — Feeding the first source and seeding the wiki
  • 14:30 — Querying the knowledge base for the first time

Graph View