Hermes Agent: Zero to Personal AI Assistant (1 Hour Course)

Hermes Agent is powerful, self-improving, easy to set up on a private server with 684+ skills. — Just Vibes (50/100)

At 0:00

The hype train is already pulling into the station! 🚂💨 'Self-improving loop' sounds like marketing speak for magic ✨.

Why this score: Overall Thesis Confirmation: The speaker sets up a massive promise: zero to personal AI assistant in an hour. Key features mentioned (self-improvement, private server compatibility) align perfectly with the web context provided.

Original quote: “Hermes Agent is one of the most powerful AI agents that I've ever played with. So, in today's video, I'm going to take you from absolutely nothing to being able to get one set up. And by the end, you're going to understand exactly how to actually get the most out of the super powerful AI agent.…”

Hermes Agent has hundreds of skills, with a significant number built-in, and can autonomously generate new skills like Excal diagrams, transcription, and voice. — Verified (95/100)

At 0:30

Numbers are slightly off, but the core claim of hundreds of skills and autonomous creation is spot-on. ✅

Why this score: Hermes Agent documentation and community posts confirm a large number of skills (e.g., 672-687 total, 87-91 built-in depending on source/version) and its capability for autonomous skill creation. Excalidraw is listed as a built-in skill. The speaker's specific numbers (684 total, 91 built-in) are very close to publicly available information.

Original quote: “there's like 684 total skills, but there's 91 that are already basically just built in once you install Hermes. So, for example, you can see that it generated me some Excal diagrams, which we'll look at in a sec. But I didn't have it install any sort of Excal skill. It just had that already. And I…”

The speaker used Hermes Agent to generate a video about itself using Hyperframes, with the agent utilizing various skills, terminal commands, and vision for analysis, though the initial result was imperfect and didn't fully use Hyperframes. — Personal Story (90/100)

At 1:52

Asking an AI to make a video about itself with specific tools, and it *actually* tries? Wild. ✅

Why this score: Hermes Agent has documented capabilities for video generation, including a 'Manim skill' for video production pipelines, and integration with 'HyperFrames Skill' for composing videos. The agent also supports multimodal vision for analyzing images and videos. The speaker's detailed account, including initial imperfections and the agent's analytical process, is consistent with the known, self-improving nature of Hermes Agent's advanced features.

Original quote: “And if you guys have seen my videos on my channel about hyperframes with claude code, basically to edit videos, I wanted to see if Hermes could do that. So I said, "Hey, can you make me a video using hyperframes about what Hermes agent is, how you work, how you remember things?" It ran all of these…”

Hermes Agent can use tools, remember preferences, create reusable skills, run scheduled automations, search conversations, integrate with Telegram, and manage workflows. — Verified (98/100)

At 1:55

This is basically the Hermes Agent features list, read straight from the docs. 😤✅

Why this score: Multiple sources confirm Hermes Agent's core capabilities, including persistent memory for preferences and past conversations, autonomous skill creation, scheduled automations, multi-platform integration (explicitly mentioning Telegram), and the ability to manage real workflows and use tools.

Original quote: “Here's a YouTube friendly version. Hey YouTube, I'm Hermes agent. I'm Nate's AI assistant running on his own infrastructure. I'm not just a chatbot in a browser. I can use tools, remember preferences, write reusable skills, run scheduled automations, search past conversations, work through…”

The speaker's Hermes agent is running various scheduled automations ('crons') like daily AI news briefings, YouTube comment monitoring, community engagement, business summaries, server checks, research reports, and follow-up reminders. — Personal Story (85/100)

At 2:10

The specific automations are personal, but Hermes' ability to run 'crons' is a core feature. 👌

Why this score: Hermes Agent is designed with a 'scheduled automations' (crons) feature that allows it to run tasks continuously and unattended. The examples provided by the speaker are plausible demonstrations of this core capability.

Original quote: “But anyways, take a look at some of these crons that my Hermes is running. A daily AI news briefing, which is posted inside of my school community, YouTube comment monitoring. So, if you guys have noticed on my YouTube videos lately, I've had an AI agent that has access to the transcript and…”

Hermes autonomously researched and generated a superior video based on simple prompts. — Just Vibes (50/100)

At 2:30

It's not just making videos; it's doing the research *first*. That's a huge leap from basic prompting. 🤯✨

Why this score: Agent Autonomy Demonstrated. The key takeaway here is that Hermes didn't just execute; it iterated. It researched 'hyperframes,' proposed installation, and then delivered a superior output based on a simple prompt about memory/skills.

Original quote: “So, it had to look into it. It did the research on its own. It asked me if it could install hyperframes. I said yes. And then it comes back with a video that's actually much, much better. So, I'm not going to play the whole thing, but here's the video that it actually came up with. It looks a lot…”

The speaker states OpenClaw was created by Peter Steinberger, who joined OpenAI, is an independent open-source project with over 350,000 GitHub stars, has a large team, frequent updates, and Nvidia built Nemoclaw on it. — Dubious (45/100)

At 5:19

350k stars? A little *too* generous with the numbers, even for OpenClaw's massive growth. 😬📈

Why this score: - Verified: Peter Steinberger is indeed the creator of OpenClaw, and he joined OpenAI in February 2026, with OpenClaw remaining an independent open-source project. - Verified: NVIDIA built NemoClaw as an open-source stack on top of OpenClaw for enterprise use. - Exaggerated: OpenClaw's GitHub stars were reported as 247,000 in early March 2026 and over 250,000 later in March/April 2026. The claim of "over 350,000" is an overstatement of publicly reported figures as of May 2026.

Original quote: “This was created by Peter Steinberger. He then joined OpenAI and OpenClaw is still an independent once again also an open source project that has over 350,000 GitHub stars. Now there's a much larger team around OpenClaw compared to Hermes and they are also doing frequent updates. Also Nvidia built…”

Sources: NVIDIA Announces NemoClaw for the OpenClaw Community, OpenClaw Surpasses React to Become the Most-Starred Software Project on GitHub

Hermes is lighter, faster, focused on self-improvement, built for tinkering with open-source models (like Llama), and the speaker switched due to OpenClaw frequently breaking after updates. — Verified (85/100)

At 5:42

✅

Why this score: - Verified: Hermes Agent is consistently described as a "self-improving AI agent" that learns from experience and autonomously creates skills, and it's compatible with open LLMs like Llama. - Verified: User reports indicate OpenClaw has experienced stability problems, including crashes, configuration errors, and issues following updates. The speaker's personal experience aligns with these documented issues.

Original quote: “differences. Hermes is also lighter, faster, focused on self-improvement. And they've come out and say like, hey, you know, this is built for people that want to tinker with open source models, Quen, Llama. I'm not necessarily using Hermes right now with open source models, but definitely something…”

Sources: Hermes 3: Advanced AI Model Features & Capabilities | Nous Research - JustCall, Hermes Unlocks Self-Improving AI Agents, Powered by NVIDIA RTX PCs and DGX Spark, OpenClaw Update Survival Guide: Why Every Version Breaks Something (And How to Fix It)

Using cloud code to manage Hermes and OpenClaw agents is a game changer for organization. — Personal Story (50/100)

At 6:30

Okay, 'game changer' for *you* maybe. Personal experience, not universal fact. 🤷‍♀️

Why this score: The speaker presents this as a personal workflow improvement, not a general statement about the technology itself. It's an anecdote about their own experience with organization.

Original quote: “context, all of your skills, you can pick out any of these agents, even codecs, and just plop it on top of your GitHub repo. And now you can play with all these different tools and see how they interact. There's just a little bit of difference sometimes with terminology, whether that's like…”

Hermes Agent automatically extracts and updates user and project information into files. — Verified (90/100)

At 8:30

This 'passive accumulation' of knowledge is a cornerstone of a self-improving agent. ✅

Why this score: Hermes Agent is designed as a self-improving AI agent with persistent memory. It extracts facts from conversations and automatically updates memory files (like user.md and memory.md) without conscious user management, loading them at session start to provide continuous context. This aligns perfectly with the claim.

Original quote: “Hermes agent understands and it's automatically going to start extracting things about you and extracting things from your projects and putting these files together. So, you don't actually have to like manually consciously think about it. As you can see, the session would start. You would go ahead…”

The speaker uses their Hermes agent to comment on YouTube videos, configured to be sarcastic. — Personal Story (70/100)

At 10:30

Alright, personal use-case noted.

Why this score: This is a personal experience shared by the speaker, demonstrating a practical application of the agent's customizable personality features. It's consistent with the 'SOUL.md' functionality.

Original quote: “If your Hermes is, you know, commenting on YouTube videos like mine, there will be some sort of personality. The one in my YouTube comments, I told it to be like very sarcastic, but not rude. And by the way guys, it's not super super important that you need to like know what a skill file looks like…”

Hermes Agent offers proactive scheduled automation with cron jobs, supporting natural language, isolated sessions, and result reporting, and is presented as a value proposition over Claude Code's 15-routine daily limit on its Max plan. — Verified (90/100)

At 12:59

✅ Whoa, they actually nailed the Claude Code limit AND Hermes' features. Impressive.

Why this score: — Hermes Agent's Cron Job capabilities: Hermes Agent documentation confirms its ability to schedule tasks with natural language or cron expressions, deliver results to origin chats or files, and run in fresh, isolated agent sessions. This aligns with the speaker's description of proactive scheduled automation. — Claude Code's routines limit: Multiple sources explicitly state that Anthropic's Claude Code, on its Max plan, has a daily limit of 15 routines. This directly verifies the speaker's specific comparison point.

Original quote: “This is where it gets super cool and this is one of the main value props for me over something like cloud code is the fact that I can just say hey spin up a cron job to do this at this time and it just does it. Cloud code obviously you have your routines you have your loops but that usually…”

Hermes Agent has a "no agent" flag to run scripts without involving the full agentic loop. — Verified (90/100)

At 14:13

✅ Straight from the docs, the "no-agent mode" exists for running plain scripts.

Why this score: — Hermes Agent documentation confirms a "no-agent mode" (or "no agent" flag) that allows running a script directly, delivering its stdout verbatim, with "zero LLM involvement". This bypasses the full agentic loop as described by the speaker.

Original quote: “And then you can do this flag for no agent, which is just a script. So, hey, I just want you to run this Python script. I don't want the agent caress loop inside of that. I just want the script to be ran.”

Hermes Agent features a self-improving loop that learns from useful experiences, persists them as memory and skills, and improves with more use. — Verified (95/100)

At 14:48

✅

Why this score: Hermes Agent is designed with a self-improving learning loop that enables it to autonomously create new skills from experience and maintain persistent memory across sessions. The agent genuinely gets more capable the longer it runs by building a deepening model of the user.

Original quote: “the self-improving loop. Hermes improves when useful experience gets persisted as memory skills and searchable history. So if you think about the loop like this, you do the work, the agent learns, you save things to memory or to agents.mmd or to, you know, user.mmd. And then you turn those…”

The self-improving loop benefits from user guidance and correction, and Hermes Agent utilizes context files like 'agents.mmd' or 'claw.md' for project context. — Verified (90/100)

At 15:19

✅

Why this score: The 'automatic' self-improvement isn't magic; it works best with active user correction and explicit saving to memory and skills. Hermes Agent also automatically discovers and loads context files such as AGENTS.md and CLAUDE.md (similar to claw.md), which define project instructions, conventions, and architecture.

Original quote: “So the nuance here is that automatic does not mean magic. The loop works best when the user corrects Hermes, asks it to save things to memory and lets it create and update skills after you've done some complex work. And there is one more kind of honorable mention which is the context file. So…”

The speaker will avoid a deep dive into terminal use for Hermes Agent, preferring Cloud Code for such tasks, and notes that while memory/soul files are global, current project context is local. — Solid (80/100)

At 15:52

Okay, fair enough on the workflow, and the tech info checks out. 👌

Why this score: The speaker's preference for Cloud Code for terminal work is a personal workflow choice. However, Hermes Agent does support both terminal and messaging interfaces like Telegram and differentiates between global files (like SOUL.md for identity/personality and MEMORY.md for persistent notes) and local project-specific context files (like AGENTS.md).

Original quote: “in today's video, I'm not going to focus too hard on the terminal. I am going to talk about the difference between using in the terminal or using it through Telegram or whatever other channel you use. But this is not going to be a deep dive on Hermes in the terminal because once again, any terminal…”

Suggests paying ~$100 for an annual plan means having it 'set up forever,' then corrects to 'for a year.' — Sketchy (35/100)

At 16:30

Almost said 'forever' for a year-long plan. The self-correction saves it from total BS. 😬🚩

Why this score: The speaker initially uses hyperbolic language ('set up forever') to describe an annual plan, then quickly corrects himself to 'for a year.' This is a minor self-correction but highlights an initial overstatement.

Original quote: “I think that you should just probably go for the annual at least because you're going to save more money. But also, you know, you pay about a 100 bucks and then you have this just set up forever. And you can also or for a year I guess”

Speaker uses a personal 'upit agents' cloud code project to manage their VPS agents, including a trading bot. — Personal Story (80/100)

At 18:30

Sounds like a practical personal solution for managing agents.

Why this score: This is the speaker's personal account of their own system ('upit agents') for managing their VPS agents, including a trading bot. As an anecdote, it describes a personal workflow and is not presented as a universal claim, therefore it's credible within that context.

Original quote: “Now, here is something that I am very, very strong on that some people might disagree with me and think that it's overengineering, but I think it's like why would you not do this for all of my VPS agents, I have created a my own cloud code project to help me manage them. So, right here, you can see…”

Suggests giving root access and passwords to Claude Code for troubleshooting and system management. — Sketchy (30/100)

At 20:30

Giving root access *and* passwords to an AI for 'fixing things' sounds like a security nightmare waiting to happen 💀🚩

Why this score: While technically possible for an AI to access a system, granting root access and directly exposing passwords to an autonomous agent, even for troubleshooting, is an extremely dubious security practice. This level of access creates significant vulnerabilities for the VPS.

Original quote: “So first of all, we have our root access. This is what we can actually give to cloud code. So if it needs to root into our um VPS and like look at our passwords or help us fix things, it can do so. It would just need the password as well.”

Speaker chooses a "one-click install" via Docker and notes that an estimated 10-minute installation finishes almost instantly. — Solid (85/100)

At 23:13

Said it'd take 10 minutes and it finished in seconds. Under-promise and over-deliver, I guess? 🚀

Why this score: The speaker specifically selects the one-click install method through the Docker manager. He then points out the system's *estimated 10-minute wait time*, expresses *doubt*, and immediately confirms the process just finished up. This directly demonstrates a very quick installation for a significant step in setting up Hermes Agent, consistent with the video's premise of a rapid setup.

Original quote: “But like I told you guys, today, what we're going to do is the one-click install. So, we would go over to our Docker manager. And this is where we'd go ahead and click install. And remember how we have our main server, but if we wanted to spin up a bunch of different Docker containers inside of…”

Claims using OpenAI Code Interpreter via ChatGPT subscription is the cheapest option for Hermes Agent, besides open-source models. — Sketchy (35/100)

At 24:30

Cheapest option 'by far,' *except* for, you know, open-source models. So... not the cheapest then? 🤡

Why this score: The speaker claims it's the 'cheapest option by far,' but immediately qualifies it with 'besides using like um you know an open source model.' This contradicts the initial strong assertion, as open-source models are often free to run locally, making them inherently cheaper than any paid subscription. While a ChatGPT subscription might be cost-effective for some users, 'cheapest by far' is an exaggeration when free alternatives exist.

Original quote: “But what I want to do is I want to use OpenAI codeex. This actually lets you take your chat GBT subscription. So 20 bucks, 100 bucks, 200 bucks a month and use that inside of Hermes agent instead of API keys. So it's going to be the cheapest option by far besides using like um you know an open…”

Hermes Agent login is successful, allowing selection of models like GPT 5.5. — Verified (90/100)

At 26:30

😤✅

Why this score: OpenAI's GPT-5.5 model was released in April 2026 and is indeed supported and available for use with Hermes Agent.

Original quote: “And when you go back to your VPS, you should be fully signed in and it should authenticate. There you go. Login successful. We get to choose a model now. So I'm obviously going to choose GBT 5.5.”

Speaker says they use Hermes/Cloud Code for troubleshooting and Hermes can perform nightly security sweeps. — Personal Story (80/100)

At 28:30

👌

Why this score: Hermes Agent is designed as a self-improving AI assistant with autonomous skill creation, which makes these claims about its utility for troubleshooting and security monitoring plausible. The speaker's personal experiences align with the agent's described capabilities.

Original quote: “If you're ever getting confused on something with your Hermes or your VPS, you just open this up and say, "I'm working on this agent. I need help with X, Y, and Z." I've actually saved myself a ton of times doing this. And also, when you want to start thinking about security and maybe getting a…”

Hermes Agent autonomously detects and resolves a gateway issue, restarting it. — Verified (90/100)

At 30:30

✅

Why this score: Hermes Agent is designed for autonomous decision-making and can handle various automation workflows. The demonstration of it identifying a stopped gateway and restarting it aligns with its self-improving and resilient execution capabilities.

Original quote: “Hello. And now we can see in the top left it is typing and it's actually able to respond. So, it said that it found the issue. The gateway was stopped and it started it again. So, that is perfect.”

Hermes Agent can research, build skills for, and automate daily GitHub backups via cron, already possessing GitHub management skills. — Verified (90/100)

At 32:30

😤✅

Why this score: Hermes Agent is designed as a self-improving AI agent with automated skill creation and continuous operation, enabling automated workflows like daily GitHub backups.

Original quote: “And so what this is going to do, it's going to do research. I'm going to show you guys how we give it that API key in the safe way. And it's also going to help us figure out, you know, it's going to probably build a skill around this. And then what we're going to do is we're going to turn it into a…”

Having two 'GitHub token' entries would cause a conflict/clash in the configuration. — Solid (75/100)

At 36:30

The clash warning is legit. Having duplicate keys under the same name is just asking for trouble! 😬🔑

Why this score: Logical necessity dictates that unique identifiers are required; having two identical 'GitHub token' entries would cause ambiguity or overwrite issues in the configuration file (likely .env).

Original quote: “But remember, we can't have two tokens in there called GitHub token or they're going to clash. So, I'm actually glad this happened because what this will do is it will have me have to show you guys how we can delete an API key.”

Speaker advises users don't need to understand complex technical details, just communicate issues clearly. — Opinion (50/100)

At 38:30

Ah, the classic 'don't understand, just tell me the error' approach to debugging. Peak abstraction 🙄.

Why this score: The speaker, after debugging a Docker environment variable issue, states that users don't need to grasp the technical intricacies, only articulate the problem. This is a pedagogical approach, pragmatic for quick fixes rather than fostering deep technical understanding.

Original quote: “Okay, so I figured it out. What happened was the agent's running inside of a container, right? And then we were doing looking at the root file for thev, but actually we needed to be looking at thev inside of that docker container. So this is the nano command that we actually need to use that gets…”

Hermes Agent can automatically create and push files to a private GitHub repo for daily synchronization. — Verified (90/100)

At 40:30

Hermes Agent automating GitHub actions? Checks out. ✅

Why this score: The speaker demonstrates Hermes Agent setting up a daily sync and pushing files to a private GitHub repository. The web context confirms Hermes Agent's capabilities include 'automated workflows' and being a 'self-improving AI agent' capable of autonomously creating and refining its own skills.

Original quote: “our skill we're about to set up where it does a daily sync it just does it with no problem. Okay. So that has been created. It gave us a link. If I click on this, it should pull up a private repo right here. You can see this is Hermes personal AI assistant. It's private. And here are all the files…”

Hermes Agent can set up complex, time-bound, and self-terminating cron jobs using natural language for tasks like managing YouTube comments or GitHub pushes. — Verified (90/100)

At 40:56

Natural language cron jobs for YouTube comments and GitHub pushes? Impressive. 😤

Why this score: The speaker demonstrates and explains Hermes Agent's ability to interpret natural language commands for creating scheduled, complex, and temporary 'cron jobs' for various tasks, including YouTube comment management and GitHub repository updates. The web context supports this with descriptions of Hermes Agent as a 'self-improving AI agent' with 'automated skill creation' and 'automated workflows'.

Original quote: “is set up our first cron job. And I want you to build a skill around this. Basically, every single night at 12 a.m., so midnight central time, I want you to push changes to this GitHub repo. This is going to be kind of our, you know, our source of truth. So, if you have any questions about that,…”

Hermes Agent functions similarly across terminal and Telegram interfaces, with Telegram offering less control, and also includes a dashboard and Kanban board. — Verified (90/100)

At 41:57

Same agent, different interfaces. And a Kanban board you don't use. Fair enough. 👌

Why this score: The speaker clarifies that Hermes Agent is functionally the same across terminal (CLI) and Telegram interfaces, with Telegram offering reduced control. The web context confirms Hermes Agent 'integrates with multiple messaging platforms (e.g., Telegram)'. The mention of a dashboard and Kanban board aligns with the 'automated workflows' aspect of an AI assistant.

Original quote: “what's the difference between using um Hermes in the terminal or using it in Telegram. So, functionally, it's really not all that different. It's the same agent in both interfaces. Telegram does not run a weaker version of it, but you have a little bit less control when you're using it in Telegram.…”

CLI is best for deep work with Hermes Agent, offering better context and commands. — Verified (90/100)

At 42:30

✅ Seems pretty standard for a robust CLI versus a chat interface.

Why this score: - Command Line Interfaces (CLI) typically offer *more direct control and visibility* into an application's state and context compared to simplified chat interfaces. - This is a common design pattern for tools intended for 'deep work' like coding.

Original quote: “The CLI, which I hardly ever use, is best for like deep work. You're building something, you're coding, you're um you know, you're living in there as kind of like your operating system. And it just has more like commands. You you have the ability obviously as we saw in here, you can see your…”

Hermes Agent autonomously sets up cron jobs, manages files, updates memory, and a nightly GitHub sync skill runs hourly, adjusting for time zones. — Verified (85/100)

At 44:34

✅

Why this score: Speaker demonstrates Hermes Agent's autonomous functions, including cron job creation, file management, memory updates, and a detailed explanation of a functional, time-zone aware GitHub sync skill.

Original quote: “So it set up the first cron job. You can see if we look at this stuff, it was able to write some files. It was able to use a cron job create tool. It used the cron job list to see if it's there. And it also updated memory at the bottom. So that's super awesome. The skill is called nightly GitHub…”

Hermes Agent skills can be created via outcome description, custom code, or installed from a library, demonstrated by installing a skill to generate a video. — Verified (85/100)

At 45:49

✅

Why this score: Speaker outlines skill creation methods and then immediately demonstrates installing a skill from a URL and commanding it to perform a task, reinforcing the agent's modularity and execution capabilities.

Original quote: “So if we want to start talking about that a little bit, you have two main paths to have your first skill. The first one is where you describe an outcome. You just saw that what I did with the GitHub sync cron. That was super super simple. The other path is you could write your own or you could…”

Used Hermes and Cloud Code to research and set up their firewall. — Personal Story (75/100)

At 46:30

Using an AI to configure your security when you're not an expert? Bold move, Cotton. 😬

Why this score: The speaker shares a personal experience of using AI agents (Hermes and Cloud Code) to assist with a technical task (setting up a firewall). While this is an anecdote and demonstrates the utility of AI, it's worth noting that relying solely on AI for critical security configurations without human expert oversight could *introduce unforeseen vulnerabilities* if the AI's understanding or implementation is flawed. It's a plausible use case for AI assistance, but *personal risk tolerance varies*.

Original quote: “And I don't really know anything about firewalls as far as like formal education. I had to do my own research, but guess how I set up my firewall? I asked Hermes and I asked Cloud Code to do research, look at our environment, look at our VPS, and help me figure out how to lock it down.”

Speaker instructs on correcting Hermes Agent errors, creating skills, and troubleshooting stale memory. — Verified (90/100)

At 48:30

Practical advice on keeping your AI in line and diagnosing issues. Solid. ✅

Why this score: The instructions provided are consistent with managing and debugging a self-improving AI agent like Hermes, which relies on its memory and skills to learn and adapt. Stale memory is a common issue in persistent learning systems, and Hermes is designed with memory management features.

Original quote: “when the agent gets something wrong twice, correct it on the spot and tell it to update the relevant skill and or memory. So, same thing. If you give the same instruction twice, ask Hermes to write a skill for it. When the agent is too verbose or off tone, you have it edit the soul. When you want a…”

Recommends separate containers for scaling Hermes agents on a VPS for isolation of keys, tools, and cost visibility. — Solid (75/100)

At 50:30

Isolation and resource management with containers? It's almost like that's their whole purpose. 🙄👌

Why this score: Utilizing containerization (e.g., Docker) for deploying multiple applications on a single Virtual Private Server (VPS) is a standard and effective practice. Containers provide process-level isolation, ensuring that each agent has its own environment, including memory, tools, and private keys, preventing conflicts ('clashing'). This isolation also facilitates better resource management and cost tracking per agent.

Original quote: “if you're doing it on one VPS I think the best way to do it is to have them each in their own container which is why in this setup I decided to do the one-click install besides the fact that it's very very easy so for example if you guys remember we have our kind of like personal main one that we…”

Recommends starting with one main personal Hermes agent to fully learn its functions before expanding to multiple agents. — Opinion (70/100)

At 52:30

Smart move for beginners. 👍

Why this score: This is sound pedagogical advice for anyone learning a new complex system. Focusing on a single instance reduces initial complexity and potential for confusion during the learning phase.

Original quote: “but once again, I would say try to get as much use out of your main personal one to start just because you are still learning how the skills work and how to work with your Hermes and how to set up everything. So, limiting the amount of like distractions really and just keeping one working on that…”

Scaling requires segmenting agents instead of using one 'mega agent' for risk reduction. — Just Vibes (50/100)

At 54:30

The whole 'don't force it' philosophy is solid advice. — But yeah, the dashboard being clunky sounds like a classic setup hurdle 🙄.

Why this score: Agent Architecture Principle - The speaker advocates for moving away from monolithic agents to segmented ones as complexity increases. - Risk Mitigation: Centralizing everything (the 'mega agent') creates high risk if one component fails. Segmentation lowers this by not putting 'all your eggs in one basket.' - Practicality Check: He correctly notes that while the dashboard exists, using it locally via Cloud Code is often easier than dealing with tunnels/gateways.

Original quote: “that is something that your main Hermes agent the one that you're building right now whether you want to call that like your COO or your executive assistant or whatever that main one is going to be able to help you figure out all that delegation and stuff like that you just have to have some…”

Hermes Agent dashboard displays a Kanban board, keys, configs, skills, plugins, and allows cron creation. — Verified (90/100)

At 56:31

✅

Why this score: The web context confirms Hermes Agent is an open-source AI with features like skill management and automated workflows, aligning with the described dashboard capabilities.

Original quote: “cananban board and you can also look at things like, you know, different keys and different configs and skills and plugins. And it's just basically a nice little visual dashboard to see what's going on here. You can also look at your crons and you can create new ones from here.”

Initial Hermes dashboard setup might be difficult, but it will work and can be saved as a skill. — Solid (80/100)

At 57:07

Sounds like every new tech tool. ✅

Why this score: The statement about initial difficulty seems a reasonable expectation for a new software setup. The ability to save processes to memory and convert them into skills aligns with Hermes Agent's described features of persistent memory and autonomous skill creation.

Original quote: “So the first time you do it you might feel a little bit like this sucks because the first time you might be pasting different things around and it might not feel like it's going to work but it will work. Just keep giving your Hermes agent the info. Keep giving it what you're doing and it will get…”