This Unlocks So Many Insane Hermes Use Cases

You've probably already heard by now that the Hermes agent is the most powerful personal agent around and that's not wrong. It actually has numerous features that make it so much better than Open Claw. But what happens when you connect it to one of the most powerful coding agents out there, Claude Code? On its own, Claude Code is great, but it's missing one crucial part from the Hermes agent, the self-evolving skill system. Paired with that, you can create workflows that are so much more autonomous, even for things that we didn't think could be automated. But other than as a personal agent, you can set it for any business that wants to automate their processes and it's really simple. But since a lot of you might be new to the Hermes agent, you don't need to worry as we're going to guide you through it. But before we get into the setup, let's start with why the self-evolving skill system matters in the first place. When we came across it, we figured it might actually be better than Open Claw. It wasn't just some random project. It's actually built by Nous Research, one of the leading labs in open-source AI and it has become one of their most popular projects. Also, here's something interesting. The Hermes agent was actually built before Open Claw. It just didn't get much hype at first. The people over at Nous Research also tried Open Claw, but they ran into issues with it, so they switched to their own setup. They saw its problems firsthand and open-sourced their solution. Most of the features Hermes has are the same as Open Claws. Just like Open Claw, you can connect it to multiple platforms, but there are two things that make it so much better. The first is persistent memory and the second is self-improving skills. Open Claw already has persistent memory, which lets it remember information about you and shape its to what you like, but that has its limits, too. Hermes goes further. It saves those memories and whenever it finds a reusable workflow in your chats, it turns it into a skill. Hermes' persistent memory is built on a really smart setup. Hermes puts a limit on how large the user.md and memory.md files can be. As you're chatting with the Hermes agent, it keeps updating those files after each run. Now, why does that limit matter? It's because of how models work. Just like you, a model also has a really bad attention span. It can only focus on a limited amount of information at a time, and it gets confused when it's given a lot of information. And all that information, from the prompts and tools to the system instructions, and on top of that your own files, is fighting for the model's attention in the context window. So, the more you fit into that context, the more the model loses focus on the actual task because all the extra information becomes noise to the agent. So, that token limit is there to prevent this from happening. Once Hermes hits the token limit on the files, the model goes through them and cuts out anything that isn't useful. It holds the newest information in memory, so the agent isn't distracted by old details you don't need anymore. Open Claw doesn't do any of this. It just lets the memory keep growing. There's another issue we faced with Open Claw. To secure it, we had to sandbox the agent ourselves. Hermes runs in a sandbox on its own. That means it runs in an isolated environment where it can't reach things it shouldn't or accidentally do something it isn't supposed to. So, it gets rid of most of the security problems Open Claw had. And if you want to run Hermes with a Claude code setup, now's the best time to do it because greedy little Dario discovered another way to make money off Claude by starting to charge for using your Claude subscription with third-party applications. After June 15th, you won't be able to use your Claude code subscription to run agents like Hermes for free. You'll have to pay Anthropic extra. Your plan will include a monthly agent SDK credit, and that credit gets spent whenever you connect a third-party app through your subscription. The same limit applies to running Claude in non-interactive mode, which is the mode a lot of agents use to run Claude code in the background without needing any permission prompts. So, until June 15th, you can keep running the Hermes agent without the ridiculous API costs. Now, setting up the Hermes agent is actually pretty simple. You just copy the install command and run it in your terminal. It first installs all the dependencies it needs, then runs the installer in interactive mode. If you want to set the agent up on the News Plan where you get their models and built-in tools, you can go for it. But, we wanted our own setup, so we went with the manual option. You can also reconfigure the agent later on using the Hermes setup command. This step is where you set up everything the agent needs. Hermes can import from your previous OpenClaw settings, so it first asks whether you want to bring those over. You can check for yourself exactly what gets brought over, which covers your user profile and credentials along with your skills and your soul file, which is basically the agent's personality and instructions. But, just like how your bloodline's been passing down that amazing height for generations, inheriting from one agent to another comes with its own issues. The login details you bring over still point to the same channels your OpenClaw agent used, and the files OpenClaw relied on don't carry over cleanly because those instructions were written specifically for OpenClaw. So, importing them just causes problems, and that's why we chose not to import ours. After that, you choose which model Hermes uses. We wanted it on Claude models through the Anthropic subscription, but when we tried it, we couldn't actually use the Claude models and got an error. Turns out Dario was already asking us to set up that extra usage even though it's not June 15th yet. So, that policy might already be rolling out gradually, but it might still work for you. Either way, we could still use Claude code in non-interactive mode right now, which is what we'll be using for most of our tasks anyway, and you can change your model provider anytime later on. Once the model is set, it asks where the agent will actually run, whether that's on hosting or a VPS you've set up. And for those of you who don't know, a VPS is basically a server you rent and run yourself. But, since we have Mac minis running entirely for this, we went with the local option. And no, we weren't the ones who caused the Mac mini shortage because unfortunately, just like you, our AI B2B SaaS business actually ran out of funding. After that, it asks you to connect whichever messaging platform you want. We chose Discord, but you can connect any of them. We won't walk through the Discord bot setup here, but you'll find the full instructions in our community AI Labs Pro. Once that's done, it asks a few more questions, and your agent is ready. You just type Hermes, and once the UI loads, you can start chatting with the agent right there. In order to tailor itself to what you actually need, it needs information about you. So, you can either keep using it for a month and let it figure you out on its own, or just tell it who you are up front before it touches any other task. If you want to set it up as a personal agent, you can either give all the information about yourself in the chat, or if you'd rather not type it all out, link it to your second brain vault instead. Just give it the path to your second brain, and tell it to onboard itself from there. And it learns everything about you that way. If you want to set it up for a specific automation use case, just provide the docs of the use case, or the general info about the company that it's being set up for. But before we move forward, let's have a word by our sponsor. So, if you're building with AI tools every day, but don't fully understand how LLMs, agents, or protocols like MCP actually work under the hood, that gap catches up fast. That's where Educative comes in as an interactive platform used by over 3 million developers with 2,300 plus courses where you code in the browser with no setup, and get AI-powered feedback on every submission. I'd start with their Essentials of Large Language Models course. In 2 hours, it breaks down how LLMs work from tokenization to attention mechanisms to RAG. You'll finish with a real mental model of what's happening under the hood. From there, MCP Fundamentals teaches you to build AI agents using the Model Context Protocol. Agentic System Design goes further, multi-agent systems that reason, plan, and act autonomously. Then the 16-hour LLM Bootcamp adds hands-on AWS labs in Bedrock, Sagemaker, and LangGraph. You'll fine-tune a model, build multi-agent systems, and ship a RAG chatbot. You're writing real code from the very first lesson, not sitting through tutorials watching someone else build. Educative has helped more than 10,000 developers land jobs at top tech companies. Try it free, link in the description. You can build a collection of skills for your Hermes agent from the skill hub. That's their official marketplace for skills and it has skills for all kinds of use cases. Hermes also comes with 90 skills installed by default. Those pre-installed skills are actually secure because they are maintained by the organization itself. That's a real difference from open claw skills, which we covered in our previous video. A huge number of those weren't safe at all with security issues like dangerous prompts and scripts that can literally transfer your data off to some server. And the skill hub actually runs a security scan on each skill and watches for these issues. That way you can add the skills you want without the same risk. Just like any other agent, you can connect any MCP you want to Hermes. But here's what separates Hermes from the rest. You can run your own Hermes setup as an MCP server itself and connect it to your other agents, letting them reach Hermes through tools so the communication goes both ways. Connecting Hermes to other agents this way fills in what those agents are missing. An agent like Claude code on its own doesn't remember anything about you and its skills don't fix or improve themselves. But through this MCP connection, you can give it access to everything Hermes can do. It also means you reach every app you've already connected to Hermes without wiring each agent up to each app separately. They just use those apps through your Hermes setup instead. To run Hermes as an MCP, you run the Hermes MCP serve command. There's no output on the terminal saying the server is up, but it's actually started running as the MCP server. To connect it to your agent, you add the Hermes MCP to the .mcp.json file and then it's usable. You can set it at project scope, which means only the project you're working on gets access. Or you can add the config to the root.cloud folder and then the Hermes MCP is available across all your projects. And speaking of skills, Hermes comes bundled with a Claude code skill which has guidance on how to use Claude code through the agent. So combined with the Hermes setup running as an MCP, this unlocks a lot for us. The Hermes agent and Claude code together open up a lot of use cases, especially in businesses where multiple automations can be set up to handle repeatable processes. One of those is connecting Claude code to your team's Slack workspace. This works really well because Hermes is basically an always running agent, while Claude code is where the actual development happens. So, we use the Hermes agent to access the team workspace. Just like with the Discord setup, we won't walk through the Slack connection here, either. But, you'll find the full guide in our community. In most workspaces, you could have a dedicated channel for a project where the whole team discusses different points about it. What you can do with the Hermes agent is ask it to create a cron job that monitors that specific channel. From the requirements being discussed there, it builds a PRD skill that evolves as those requirements change. Having the PRD as a skill is really helpful, especially during the sessions where you're actually developing the product. Whenever it's needed, it pulls the relevant parts of the PRD into the context. So, the project stays aligned with the original requirements. The PRD on its own might work, too. But, for the same reason we talked about earlier, the agent sometimes gets confused about what it needs to pay attention to. A skill gets called whenever it's needed and stays in the fresh part of the context window where the model is actually paying attention. So, Hermes creates the skill the way you instructed and runs it every 30 minutes as a cron job. This way, whenever a requirement change gets discussed in the channel, it updates the PRD and the Hermes agent makes sure those changes flow both ways. So, the skill created inside your project stays updated, too. At this point, you might be thinking, "Since we already have an MCP connected for the Hermes agent, why not just use a tool to pull the information from that Slack channel and have the agent act on it?" The reason is that the Slack MCP has a limitation. It can't read the entire conversation history by default. It only reads the messages it's tagged in, and it won't pull the full history unless the tagged message specifically needs that context. So, setting it up through the Hermes agent is the better route because it can sync the information directly from there. From there, you can also ask it to implement any feature using Cloud Code in non-interactive mode directly through the Hermes agent channels. It loads that Cloud Code skill we talked about earlier, then launches Cloud Code and uses it to build the feature. Also, if you are enjoying our content, consider pressing the hype button because it helps us create more content like this and reach out to more people. You can [snorts] also bolt Hermes onto a deployed app, whether you're building it for yourself or for a client. So, if you have a deployed app built with Cloud Code, you can create skills for monitoring and health checks that guide the agent on how to monitor the running app because Cloud Code has the best context on what the app actually needs. Then, you import those skills into your Hermes agent. You can set up a cron job for that, basically a task that runs on its own on a schedule, and let the agent monitor both the hosted app and the code. We also told it that if it finds an issue by running the skill and updates it, it should sync those skills back to the local project. So, Cloud Code has context on them, too. So, this is how its self-evolving skills help in setting up a continuous health check that gets better every time it runs. So, once you give Hermes the prompt, it sets up the cron job for you. You can test run it to see if it's configured properly. It gives you a report in whichever channel you set up, and in our case, it reported in Discord. And with the MCP configured, you can get those reports right inside Cloud Code along with all the suggested fixes from other team members and implement them directly in your project. Or, you can push those fixes yourself or even set up the Hermes agent to fix the issues it found using Cloud Code. If you want to found the next big AI B2B company and automate everything like we did with Hermes, you should be in AI Labs Pro. That's where you'll find the setup guides from this video along with all the other resources and goodies we've put together. You'll also get to meet a bunch of like-minded nerds, including our team. The link's in the description, and you can check that out. That brings us to the end of this video. If you'd like to support the channel and help us keep making videos like this, you can do so by using the super thanks button below. As always, thank you for watching and I'll see you in the next one.