Shows how to build a second-brain setup by connecting the Hermes agent to an Obsidian vault so skills and notes become visible, editable markdown, then setting it all up on a Hostinger VPS where an AI agent (Pi) does the DevOps install and Obsidian Sync keeps files synced across MacBook, phone, and VPS.
David Ondrej31 minTranscript found
Quick learning frame
Read this before watching.
Agent ops treats agents like services: observable state, queues, permissions, logs, recovery, and post-run review.
New playlist item from David Ondrej; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to turn your files into agent-accessible 'living files' in an Obsidian vault synced to a VPS, so an autonomous agent like Hermes can read, edit, and act on your second brain across devices.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Project state
02Session
03Queue/Kanban
04Tools
05Logs
06Recovery
07Post-run review
Deep lesson
Turn this video into working knowledge.
6,607 cleaned transcript words reviewed across 1,948 timed caption segments.
Thesis
Obsidian Just 10x’d Everyone’s Hermes Agent teaches a practical hermes operations move: Shows how to build a second-brain setup by connecting the Hermes agent to an Obsidian vault so skills and notes become visible, editable markdown, then setting it all up on a Hostinger VPS where an AI agent (Pi) does the DevOps install and Obsidian Sync keeps files synced across MacBook, phone, and VPS.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:57
Living vs dead files
“just edit it as a skill, if you have a lot of skills. For example, right now, I have 185 skills myself. Roughly half of them are pre-built into Hermes. The other half are my custom skills. But,...”
A 'dead file' is anything an AI agent can't access (on Google Drive, a hard drive, sitting unused), making it useless; a 'living file' is a markdown file any agent can use as skill, reference, memory, or context, and Obsidian is both human-readable and agent-readable, letting you see and edit the agent's skills (he has 185) visually instead of digging through code or config. Take one deep-research output or SOP you have buried in Google Drive and convert it into a markdown file inside an Obsidian vault so an agent could actually use it.
9:40
Always-on vs on-demand
“Agent. Boom. And again, I have videos on all of this, so feel free to watch them after this one, but you can use any other agent, Claude, Code, CodeX, Hermes, whatever. We're going to use Pi to...”
The agent doesn't silently read your whole vault (that would bloat the context window and cost tokens); instead a tiny always-on core memory, the system prompt called soul.md, holds essentials like your name and answer preferences, while most knowledge (skills, notes) is loaded only on demand when relevant. Write your own soul.md-style core memory: the handful of always-on facts and preferences an agent should know, kept deliberately short, separate from your on-demand notes.
26:04
Agent installs the VPS
“synced to my MacBook. Okay, so basically, what I did is I sent a screenshot of this prompt, which again included in the second link below the video, and this will sync all of the Hermes skills with...”
Rather than being a DevOps expert, he SSHes into a Hostinger VPS and lets the Pi agent (running Opus 4.5 since Fable was disabled) run all the terminal commands, monitor the Hermes install, set up Obsidian Sync with encryption, and self-debug; sensitive passwords are pasted directly into the terminal, not to the agent, so they stay private and off Anthropic. Practice delegating one setup task to an AI agent by pasting a install command and asking it to run and monitor it, while manually entering any secrets directly into the terminal rather than the chat.
01
Project state
Start with this video's job: Shows how to build a second-brain setup by connecting the Hermes agent to an Obsidian vault so skills and notes become visible, editable markdown, then setting it all up on a Hostinger VPS where an AI agent (Pi) does the DevOps install and Obsidian Sync keeps files synced across MacBook, phone, and VPS. Treat "Project state" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:57, where the video says: “just edit it as a skill, if you have a lot of skills. For example, right now, I have 185 skills myself. Roughly half of them are pre-built into Hermes. The other half are my custom skills. But,...”
02
Session
Use "Session" to locate the part of the hermes operations mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 9:40, where the video says: “Agent. Boom. And again, I have videos on all of this, so feel free to watch them after this one, but you can use any other agent, Claude, Code, CodeX, Hermes, whatever. We're going to use Pi to...”
03
Queue/Kanban
Turn "Queue/Kanban" into the reusable artifact for this lesson: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria. This is where watching becomes something you can inspect and reuse.
04
Tools
Use "Tools" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Logs
Use "Logs" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Recovery
Use "Recovery" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
07
Post-run review
Connect "Post-run review" to Obsidian Just 10x’d Everyone’s Hermes Agent by naming the claim, the evidence, and the artifact it should produce.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
Example
Hermes operations proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the hermes operations pattern.
Example
Teach-back module
Transform the lesson into a definition, a Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
treating UI features as reliability
missing logs
no stop/recover path
Letting the lesson drift into feature cheerleading.
Letting the lesson drift into ops advice without logs/state.
Letting the lesson drift into assuming reliability from a demo alone.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: Shows how to build a second-brain setup by connecting the Hermes agent to an Obsidian vault so skills and notes become visible, editable markdown, then setting it all up on a Hostinger VPS where an AI agent (Pi) does the DevOps install and Obsidian Sync keeps files synced across MacBook, phone, and VPS.
02
Explain the practical stakes without hype: New playlist item from David Ondrej; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: Obsidian Just 10x’d Everyone’s Hermes Agent
- URL: https://www.youtube.com/watch?v=Q0HTefP9DFU
- Topic: Creative Automation
- My current learning frame: Spin up a VPS, have an AI agent run the Hermes and Obsidian Sync install for you, then create a note on the VPS and confirm it syncs to your Obsidian vault and that Hermes can read it, turning your files into living files.
- Why this matters: New playlist item from David Ondrej; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:57 / Evidence 1: "just edit it as a skill, if you have a lot of skills. For example, right now, I have 185 skills myself. Roughly half of them are pre-built into Hermes. The other half are my custom skills. But,..."
- 2:42 / Evidence 2: "of caught on, it needs to be able to be used by any AI agent as a skill, reference, memory, context, part of a prompt, anything. It just needs to be usable by AI agent to do tasks..."
- 6:03 / Evidence 3: "talking about that specific thing. So, the way to understand it is that the memory, the core memory, the system prompt is always on, and your notes and skills are only pulled in when relevant. Now, let's focus..."
- 9:40 / Evidence 4: "Agent. Boom. And again, I have videos on all of this, so feel free to watch them after this one, but you can use any other agent, Claude, Code, CodeX, Hermes, whatever. We're going to use Pi to..."
- 11:13 / Evidence 5: "think is the best for like coding and managing your servers, or we could just delegate the Hermes setup installation to Pi. And you can talk to Pi Agent in plain English, which I have running uh Opus..."
- 13:58 / Evidence 6: "observability graphs, you know, being able to set limits per model per API key, complete controls. So, I'm building that for myself and my team. I might make it public, we'll see. Depends if there's interest in it."
- 26:04 / Evidence 7: "synced to my MacBook. Okay, so basically, what I did is I sent a screenshot of this prompt, which again included in the second link below the video, and this will sync all of the Hermes skills with..."
Video-aware target:
- Prompt lane: Hermes operations
- Mechanism to extract: Identify the operations control that makes long-running agent work visible, recoverable, or safer.
- Artifact to produce: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
- Artifact must include: health check; state model; permission boundary; log source; recovery action
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Identify the operations control that makes long-running agent work visible, recoverable, or safer. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A Hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Project state -> Session -> Queue/Kanban -> Tools -> Logs -> Recovery -> Post-run review
- answers to these source questions: What operational failure is prevented? | What state is visible? | What can be recovered or redirected?
- 3 concrete examples that apply the video idea to real agentic work, such as Hermes Kanban triage; local model endpoint check; agent swarm recovery review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: treating UI features as reliability; missing logs; no stop/recover path
- a checklist for the next real workflow, focused on: status, model/backend, tools, logs, recovery
- one practical exercise with a clear done signal: Write a runbook for restarting one stuck Hermes-style agent session.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "Obsidian Just 10x’d Everyone’s Hermes Agent", not a generic Creative Automation essay.
- Ground each ops recommendation in transcript evidence about state, queues, models, tools, security, logs, or recovery.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: feature cheerleading; ops advice without logs/state; assuming reliability from a demo alone.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a hermes-style agent-ops runbook with health checks, state transitions, logs, recovery steps, and review criteria..
A reusable artifact with a done signal and one verification step.03
Hermes operations teach-back card
Explain the hermes operations mechanism to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
What is the difference between a dead file and a living file?
How does Hermes avoid bloating the context window with the whole vault, and what is soul.md?
How does the presenter avoid needing to be a DevOps expert to set up the VPS, and how does he keep passwords private?
Source shelf
Use the video as a doorway, then verify with primary sources.
