Hermes is installed—now let’s give it a brain without a surprise API bill. 🧠 Class 5 walks through three routes: - Run a model locally with Ollama. - Connect a supported subscription you already have. - Experiment with hosted free tiers such as OpenRouter. 📘 Your companion manual is ready: copyable commands, the desktop setup steps from the final video, the 64K context fix, troubleshooting, and a practical file-writing exercise. Download the HTML from the lesson’s Resources and open it in your browser. Local inference has no per-token model bill; subscriptions and hosted free tiers have their own limits. The manual also includes current notes on tool support, cloud vision and provider billing. ▶️ Watch Class 5 + download the manual Prefer YouTube? Watch the final video here. 🎯 Your challenge: get ONE route running and make Hermes read a practice file, write a summary, and read the saved result back using a tool. Then open the file yourself to verify it. Reply below with your route, OS/RAM, exact model, and whether the exercise passed. If you’re stuck, share the error—leave out API keys and private information. Next class: Your First Conversation. 🚀

🧠 What actually happens when you hit send? You chat with your agent every day — but do you know what it's doing in there? 👀 Most people use Hermes like a chatbot. Huge mistake. In Class 3 we open the hood and follow one message through the entire machine: Gateway → Guard → Prompt Assembly → the Loop → Post-flight. You will never look at your agent the same way again. 🤯 🎁 What you'll discover - 🧠 Why Hermes "forgets everything" every single turn — and the memory-tattoo system that rescues it - 💸 How prompt caching slashes your token bill 50–90% (same answers, fraction of the cost) - 🔄 The operating loop — Perceive → Reason → Act → Iterate — on a 90-iteration budget with 40+ tools - 🛡️ The Approval Inbox: the safety gate standing between your agent and disaster - ✅ Verify-on-Stop — why Hermes checks its own homework before it reports back The LLM is the engine. Hermes is the whole car. 🏎️ After this class you'll finally know what you're driving. 👉 Take the class Class 3 — How Hermes Actually Thinks is live now: https://www.skool.com/tolearnaiautomation-4236/classroom/43a05e49?md=c9f9af8b321442a7bd8252d0ac7be314 Next up: Install in 10 Minutes ⏱️ — you don't need it yet… but you'll want it. 😉

Here's what Klaus asked me a couple of days ago: If any of you have requests for videos or topics you're interested in, just post them in the group. I'll make a post or dedicated videos for them! https://www.skool.com/tolearnaiautomation-4236/classroom/cef5ea3d?md=7839fdd9d8864ed0b935fabca8fb8932 @klaus

Hi everyone, I am Javi. I am glad to join this community and learn more about AI automation and OpenClaw security setups. My main goal is to master the installation, security, and day-to-day use of OpenClaw on a Mac Mini. I am looking forward to learning from all of you and growing my skills here.