I Rebuilt Hermes in Claude Code (It’s Ridiculously Good)
This video walks through which Hermes agentic-OS features (identity layer, memory injection, self-learning loop) the creator deliberately rebuilt inside Claude Code, and why owning each layer beats installing an off-the-shelf stack like Hermes or OpenClaw.
Simon Scrapes13 minTranscript found
Quick learning frame
Read this before watching.
Creative automation uses agents to accelerate production while keeping human taste in story, pacing, selection, and critique.
New playlist item from Simon Scrapes; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: Evaluating off-the-shelf agentic frameworks against a self-built modular setup, and redesigning identity, memory, and skill-creation layers so they scale across multiple clients instead of accumulating maintenance debt.
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.
01Brief
02Source
03Generation
04Selection
05Edit
06Taste Review
Deep lesson
Turn this video into working knowledge.
2,665 cleaned transcript words reviewed across 792 timed caption segments.
Thesis
I Rebuilt Hermes in Claude Code (It’s Ridiculously Good) teaches a practical creative automation move: This video walks through which Hermes agentic-OS features (identity layer, memory injection, self-learning loop) the creator deliberately rebuilt inside Claude Code, and why owning each layer beats installing an off-the-shelf stack like Hermes or OpenClaw.
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.
1:24
Read issues first
“an example, the infamous self-arning loop on Hermes, the bit that everyone celebrates, has no external guardrails. So, we're effectively telling it to build its own skills automatically, then grade your own homework. So, we've got the self-...”
Off-the-shelf agent systems are fast to start but make you inherit someone else's architecture, assumptions, and problems; reading a repo's open issues before installing surfaces hidden costs you can't fix without understanding the layers underneath. Before adopting any popular agent framework, open its GitHub issues tab and list the recurring assumptions or unfixable problems you'd be inheriting.
7:44
Multi-client identity
“keyword search, we can take other memory systems like mem search in this example and make recall much more powerful. And that's exactly what we've done with our own agentic operating system. So we're still using some patterns...”
Hermes models identity as a single memory.md and user.md for one person/business, so running multiple clients means separate full installs; a folder structure that injects per-client shared brand context (voice, ICP, visual identity) while sharing skills across clients avoids duplicated maintenance. Sketch a folder layout that separates per-client brand context files from a shared skills directory, so a voice change updates in one place across all clients.
8:25
Memory: inject vs recall
“self-learning loop we talked about earlier. So, one of Hermes's biggest selling points is the self-arning loop. So, an agent finishes a task, it's going to write itself effectively a new skill every time and use it the...”
Hermes autosaves and summarizes every turn and injects a capped (~1,300 token) recent-memory snapshot well, but its long-term recall searches by keyword not meaning, so memories are lost unless you recall the exact words used; pairing Hermes-style injection with a semantic/meaning-based recall layer (e.g. mem-search) fixes the gap. Map the three memory levels (storage, injection, recall) for your own setup and pick a semantic search tool to replace keyword-only long-term recall.
01
Brief
Start with this video's job: This video walks through which Hermes agentic-OS features (identity layer, memory injection, self-learning loop) the creator deliberately rebuilt inside Claude Code, and why owning each layer beats installing an off-the-shelf stack like Hermes or OpenClaw. Treat "Brief" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:24, where the video says: “an example, the infamous self-arning loop on Hermes, the bit that everyone celebrates, has no external guardrails. So, we're effectively telling it to build its own skills automatically, then grade your own homework. So, we've got the self-...”
02
Source
Use "Source" to locate the part of the creative automation workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 7:44, where the video says: “keyword search, we can take other memory systems like mem search in this example and make recall much more powerful. And that's exactly what we've done with our own agentic operating system. So we're still using some patterns...”
03
Generation
Turn "Generation" into the reusable artifact for this lesson: A creative workflow board with critique criteria and review checkpoints. This is where watching becomes something you can inspect and reuse.
04
Selection
Use "Selection" 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
Edit
Use "Edit" 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
Taste Review
Use "Taste Review" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a creative workflow board with critique criteria and review checkpoints..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism 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.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This video walks through which Hermes agentic-OS features (identity layer, memory injection, self-learning loop) the creator deliberately rebuilt inside Claude Code, and why owning each layer beats installing an off-the-shelf stack like Hermes or OpenClaw.
02
Explain the practical stakes without hype: New playlist item from Simon Scrapes; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source -> Generation -> Selection -> Edit -> Taste Review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative workflow board with critique criteria and review checkpoints.
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: I Rebuilt Hermes in Claude Code (It’s Ridiculously Good)
- URL: https://www.youtube.com/watch?v=wdc1OFWDxlU
- Topic: Creative Automation
- My current learning frame: Pick one Hermes feature from this video (identity, memory, or the self-learning loop) and design a modular Claude Code version of it that shares context across two distinct client brands without duplicating files.
- Why this matters: New playlist item from Simon Scrapes; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:24 / Evidence 1: "an example, the infamous self-arning loop on Hermes, the bit that everyone celebrates, has no external guardrails. So, we're effectively telling it to build its own skills automatically, then grade your own homework. So, we've got the self-..."
- 3:30 / Evidence 2: "identity layer. So the agent needs to know who you are, who your business is, and what you stand for. Otherwise, every AI output is going to sound like an AI output. So in Hermes, this represents itself..."
- 5:20 / Evidence 3: "folder structure so you can handle multiple clients or multiple brands but still share the relevant shared context so you don't have to maintain it in multiple places. It's just one single install versus Hermes for multiple clients..."
- 7:44 / Evidence 4: "keyword search, we can take other memory systems like mem search in this example and make recall much more powerful. And that's exactly what we've done with our own agentic operating system. So we're still using some patterns..."
- 8:25 / Evidence 5: "self-learning loop we talked about earlier. So, one of Hermes's biggest selling points is the self-arning loop. So, an agent finishes a task, it's going to write itself effectively a new skill every time and use it the..."
- 9:59 / Evidence 6: "created personally in-house in our own Agentic OS a whole logic around how to tackle this and we call this skill systems. So a skill shouldn't be just a one-off task. A skill is a modular component that..."
- 12:11 / Evidence 7: "everyone, right? It's just a personal choice. Now, I'm definitely not saying my version of the Aentic operating system or every custom version is better than Hermes in every way. Absolutely not. But I understand exactly what assumptions..."
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, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative workflow board with critique criteria and review checkpoints.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Brief -> Source -> Generation -> Selection -> Edit -> Taste Review
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
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 "I Rebuilt Hermes in Claude Code (It’s Ridiculously Good)", not a generic Creative Automation essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, 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 creative workflow board with critique criteria and review checkpoints..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson 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 did the creator do before installing Hermes that most people skip, and what hidden cost does it surface?
Why does Hermes' identity model force separate installs for multiple clients, and what folder structure fixes the maintenance problem?
What are Hermes' three memory levels, and which one is broken and how is it fixed?
Source shelf
Use the video as a doorway, then verify with primary sources.
