Claude Fable 5 Just Built the Ultimate Agent Harness
Pat Simmons builds an agentic development environment (ADE) called Damon from scratch with Claude Fable 5, giving him one Electron app that organizes agents by category and opens Chrome-style terminal tabs, each running any model, Claude, Codex/GPT, or open-source models via OpenRouter. He iterates from mockup to Mac app in a few passes and forks the Hermes repo to give each agent self-improving memory files.
Pat Simmons19 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 Pat Simmons; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to iteratively direct Claude Fable 5 with reference screenshots and open-source repos to assemble a multi-agent, multi-model ADE with persistent memory instead of scattered chat windows.
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.
01Gateway
02Session
03Queue
04Tools
05Logs
06Recovery
Deep lesson
Turn this video into working knowledge.
4,312 cleaned transcript words reviewed across 1,186 timed caption segments.
Thesis
Claude Fable 5 Just Built the Ultimate Agent Harness teaches a practical hermes + agent ops move: Pat Simmons builds an agentic development environment (ADE) called Damon from scratch with Claude Fable 5, giving him one Electron app that organizes agents by category and opens Chrome-style terminal tabs, each running any model, Claude, Codex/GPT, or open-source models via OpenRouter. He iterates from mockup to Mac app in a few passes and forks the Hermes repo to give each agent self-improving memory files.
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.
0:13
The ADE vision
“inside Cloud Code and Codeex, and absolutely no system to any of it. If you're using an agent platform, the context switching alone is killing your productivity. But what if I told you there's one app that will...”
The core design borrows from open-source ADEs like Superset (agents on the left, tabs on top) while avoiding closed tools like Conductor: categories such as YouTube on the left, agents (script writer, motion graphics, analytics) under them, and Chrome-like terminal tabs where each tab is its own CLI session and repo/worktree. Sketch your own ADE layout listing one category and three agents under it, noting what each terminal tab would run.
11:54
Any model via OpenRouter
“ahead and spawn agents and do this next. All right, our new build is live. So, we have an ability now to choose from different models. Claude, OpenAI, Kimmy, Miniax, GLM, and we should have little indicators, little...”
Beyond logging into a Claude subscription and Codex/GPT, a new-tab model picker adds open-source models like Kimi K2, MiniMax M3, and GLM by loading the Claude Code harness with the Anthropic base URL pointed at the OpenRouter endpoint plus your OpenRouter API key and a model string like moonshot/kimi-k2; a missing-authentication-header error was fixed by re-prompting Fable. Create an OpenRouter API key with credits and trace how the app maps the Anthropic base URL to an OpenRouter model string.
14:51
Fork Hermes for memory
“memory, and kind of self-improving system with their harness, and use this for our own agents. All right. So, Fable grabbed the Hermes GitHub repo, brought over exactly how they structure this agent.mmd, userd, memory.mmd, and this should...”
Because closing a tab wiped the agent's context, Pat had Fable fork the open-source Hermes repo to bring over its agents.md, user.md, and memory.md structure so each agent has a self-improving memory system, then noted the templates ship generic (calling the agent an 'autonomous coding agent') and must be edited per agent. Open one generated agent.md and rewrite it to state that agent's real name, role, and the files it should update after each session.
01
Gateway
Start with this video's job: Pat Simmons builds an agentic development environment (ADE) called Damon from scratch with Claude Fable 5, giving him one Electron app that organizes agents by category and opens Chrome-style terminal tabs, each running any model, Claude, Codex/GPT, or open-source models via OpenRouter. He iterates from mockup to Mac app in a few passes and forks the Hermes repo to give each agent self-improving memory files. Treat "Gateway" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:13, where the video says: “inside Cloud Code and Codeex, and absolutely no system to any of it. If you're using an agent platform, the context switching alone is killing your productivity. But what if I told you there's one app that will...”
02
Session
Use "Session" to locate the part of the hermes + agent ops workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 11:54, where the video says: “ahead and spawn agents and do this next. All right, our new build is live. So, we have an ability now to choose from different models. Claude, OpenAI, Kimmy, Miniax, GLM, and we should have little indicators, little...”
03
Queue
Turn "Queue" into the reusable artifact for this lesson: An ops checklist for running and recovering local agent work. 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.
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 an ops checklist for running and recovering local agent work..
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: Pat Simmons builds an agentic development environment (ADE) called Damon from scratch with Claude Fable 5, giving him one Electron app that organizes agents by category and opens Chrome-style terminal tabs, each running any model, Claude, Codex/GPT, or open-source models via OpenRouter. He iterates from mockup to Mac app in a few passes and forks the Hermes repo to give each agent self-improving memory files.
02
Explain the practical stakes without hype: New playlist item from Pat Simmons; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Gateway -> Session -> Queue -> Tools -> Logs -> Recovery sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: An ops checklist for running and recovering local agent work.
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: Claude Fable 5 Just Built the Ultimate Agent Harness
- URL: https://www.youtube.com/watch?v=HhWwllcbc2g
- Topic: Hermes + Agent Ops
- My current learning frame: Using Claude Fable 5 plus reference screenshots and the Superset and Hermes repos, iterate a simple ADE mockup into a running app with a model picker and per-agent memory markdown files, then configure one agent end to end.
- Why this matters: New playlist item from Pat Simmons; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:13 / Evidence 1: "inside Cloud Code and Codeex, and absolutely no system to any of it. If you're using an agent platform, the context switching alone is killing your productivity. But what if I told you there's one app that will..."
- 3:23 / Evidence 2: "start brainstorming this. So, we will open up a new session in terminal here with Fable 5 model Fable. I'm going to paste in this prompt. I will put it on screen. Essentially what I am saying is..."
- 6:28 / Evidence 3: "to add a profile photo, connecting the CLIs, stripping back some of these extraneous designs and functions here. And while that builds, Claude and I just thought of the name of this application, which is going to be..."
- 9:26 / Evidence 4: "locally. Oh wow. Okay, it already opens up claude. So okay, yeah, here is the folder that it's opening up locally. ad default agents and then it's just this string and then /worktree and I can go yes..."
- 11:54 / Evidence 5: "ahead and spawn agents and do this next. All right, our new build is live. So, we have an ability now to choose from different models. Claude, OpenAI, Kimmy, Miniax, GLM, and we should have little indicators, little..."
- 14:51 / Evidence 6: "memory, and kind of self-improving system with their harness, and use this for our own agents. All right. So, Fable grabbed the Hermes GitHub repo, brought over exactly how they structure this agent.mmd, userd, memory.mmd, and this should..."
- 18:36 / Evidence 7: "with your agent on what you want the agent to do. But that's how simple setup is as well. Now I could keep going with this and building out more agents because we've really only scratched the surface..."
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: An ops checklist for running and recovering local agent work.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Gateway -> Session -> Queue -> Tools -> Logs -> Recovery
- 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 "Claude Fable 5 Just Built the Ultimate Agent Harness", not a generic Hermes + Agent Ops 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.
A chat UI is an agent operating system.
A chat UI is only the surface. Ops requires state, logs, permissions, queues, and recovery.
Swarms are automatically more powerful.
Parallel agents help only when work is separable and verifiable.
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 an ops checklist for running and recovering local agent work..
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.
How is Pat's ADE (Damon) organized on screen?
How does the app run open-source models like Kimi K2 or MiniMax M3?
Why did Pat fork the Hermes repo, and what did it provide?
Source shelf
Use the video as a doorway, then verify with primary sources.
