Hermes + Agent Ops / Foundation

Hermes Agent 5.0 (New Upgrades): HERMES BECAME ULTRA-HERMES!

AICodeKing reviews Hermes Agent 0.16, the 'surface release': a native desktop app for macOS/Linux/Windows with remote gateway support, a web dashboard grown into a full admin panel, quick setup via Naos portal, a fuzzy-search model picker with hourly catalog refresh, /undo, a pruned skill set with a trusted Nvidia tab, and a security pass including a Starlette CVE pin.

AICodeKingWatchTranscript 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 AICodeKing; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Skill you build: The ability to operate Hermes Agent through its new surfaces — choosing between local and remote-gateway setups, routing across models with the improved picker, and keeping the skill set and security posture clean for multi-platform agent work.

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.

1,885 cleaned transcript words reviewed across 629 timed caption segments.

Thesis

Hermes Agent 5.0 (New Upgrades): HERMES BECAME ULTRA-HERMES! teaches a practical hermes + agent ops move: AICodeKing reviews Hermes Agent 0.16, the 'surface release': a native desktop app for macOS/Linux/Windows with remote gateway support, a web dashboard grown into a full admin panel, quick setup via Naos portal, a fuzzy-search model picker with hourly catalog refresh, /undo, a pruned skill set with a trusted Nvidia tab, and a security pass including a Starlette CVE pin.

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.

0:49

Surfaces over internals

“Hermes Desktop. I already showed the desktop app in detail, so I'm not going to repeat the whole walk-through here. But, the important change in 0.16 is that the desktop app is now part of the main Hermes...”

The release name fits: Hermes already had powerful internals, but if the only way to understand an agent is config files and terminal logs most people never use it properly — the native desktop app (chat window, streaming, searchable sessions, drag-and-drop files, clipboard paste, command palette, status-bar model picker) makes sessions, models, skills, cron, and sub-agents visible. Install the Hermes desktop app and locate five internals it surfaces — sessions, model picker, skills, profiles, and sub-agents — without opening a config file.

4:58

Routing and rewind

“model when the job is harder. You can use local models when privacy or cost matters, and you can route all of that from the same system. So, improving the model picker is not just a UI polish...”

The model picker now has fuzzy search across desktop, dashboard, TUI, and CLI, groups multi-endpoint providers cleanly, and refreshes the catalog hourly (surfacing new models like DeepSeek-V4-Flash and Minimax-M3 with 1M context), while /undo lets you take back the last N turns and resend in CLI, TUI, Telegram, and Discord — rewind instead of restarting a session after one bad prompt. Practice the recovery loop: send a deliberately wrong prompt, use /undo to rewind, edit the message, and resend — then fuzzy-search the picker to switch to a cheaper model for a simple task.

6:28

Prune and harden

“because skills are powerful, but too many irrelevant skills can make the agent messier. It can increase context, confuse selection, and make the UI feel crowded. So, I like this change. They are not just adding more and...”

Hermes trimmed redundant default skills, moved heavy niche ones to optional installs, and added relevance gates so context-specific skills don't clutter irrelevant setups — pruning matters because too many skills bloat context and confuse selection — plus a trusted Nvidia skills tab joins OpenAI/Anthropic/Hugging Face, and security hardening (Starlette CVE-2026-48710 pin, SSRF checks, Docker pattern guards) backs the added power. Audit your agent's installed skills and remove or gate any that never trigger in your actual workflows, noting how it changes context noise.

01

Gateway

Start with this video's job: AICodeKing reviews Hermes Agent 0.16, the 'surface release': a native desktop app for macOS/Linux/Windows with remote gateway support, a web dashboard grown into a full admin panel, quick setup via Naos portal, a fuzzy-search model picker with hourly catalog refresh, /undo, a pruned skill set with a trusted Nvidia tab, and a security pass including a Starlette CVE pin. Treat "Gateway" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:49, where the video says: “Hermes Desktop. I already showed the desktop app in detail, so I'm not going to repeat the whole walk-through here. But, the important change in 0.16 is that the desktop app is now part of the main Hermes...”

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 4:58, where the video says: “model when the job is harder. You can use local models when privacy or cost matters, and you can route all of that from the same system. So, improving the model picker is not just a UI polish...”

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.

Transcript-derived moments

Use timestamps to study the actual video.

Quality check

Do not count this as learned until these are true.

01

State the transcript-backed claim in your own words: AICodeKing reviews Hermes Agent 0.16, the 'surface release': a native desktop app for macOS/Linux/Windows with remote gateway support, a web dashboard grown into a full admin panel, quick setup via Naos portal, a fuzzy-search model picker with hourly catalog refresh, /undo, a pruned skill set with a trusted Nvidia tab, and a security pass including a Starlette CVE pin.

02

Explain the practical stakes without hype: New playlist item from AICodeKing; 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: Hermes Agent 5.0 (New Upgrades): HERMES BECAME ULTRA-HERMES!
- URL: https://www.youtube.com/watch?v=woSihN3IKyc
- Topic: Hermes + Agent Ops
- My current learning frame: Set up Hermes 0.16 with the desktop app pointed at a remote gateway (or quick setup via Naos portal locally), configure one messaging channel from the web dashboard, then prune the default skill set to just what your workflow uses.
- Why this matters: New playlist item from AICodeKing; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:49 / Evidence 1: "Hermes Desktop. I already showed the desktop app in detail, so I'm not going to repeat the whole walk-through here. But, the important change in 0.16 is that the desktop app is now part of the main Hermes..."
- 2:34 / Evidence 2: "Each profile can point to its own remote host, and you can run concurrent sessions across profiles in one window. So, instead of Hermes being one local agent tied to one local setup, it starts to feel more..."
- 4:58 / Evidence 3: "model when the job is harder. You can use local models when privacy or cost matters, and you can route all of that from the same system. So, improving the model picker is not just a UI polish..."
- 6:28 / Evidence 4: "because skills are powerful, but too many irrelevant skills can make the agent messier. It can increase context, confuse selection, and make the UI feel crowded. So, I like this change. They are not just adding more and..."
- 9:33 / Evidence 5: "security and bug fix work makes the whole thing feel more serious. It is still not a basic chatbot. And if you only want a simple AI coding assistant, Hermes may still be overkill. But, if you care..."

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 "Hermes Agent 5.0 (New Upgrades): HERMES BECAME ULTRA-HERMES!", 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.

Why is Hermes 0.16 called the 'surface release'?

What does the /undo command do and where does it work?

Why did Hermes trim its default skill bundle, and what new trusted source was added?

Source shelf

Use the video as a doorway, then verify with primary sources.

ReadingOpen WebUI Docsdocs.openwebui.com/ReadingHermes Agent Docshermes-agent.nousresearch.com/docs