SaturdAI.
Hands-on Agentic AI with Hermes Agent
A free, live, instructor-led 2-week intensive. Build and deploy a real Hermes agent — fundamentals, LLM routing, RAG, MCPs, tool calling, and a production deploy — running against real local LLMs on a DGX Spark supercomputer and an Apple Mac Mini. No prerequisites. Just curiosity. Everyone welcome.
Mon–Wed–Fri, 6–7pm MST, Fri Sep 25 – Fri Oct 9, 2026. Day 1 is a talk-only kickoff — hands-on labs run Day 2 through Day 7.
Watch the Recordings
July 4 (Morning) · Jul 4, 2026
Day 2 · Jul 7, 2026
Day 3 · Jul 8, 2026
July 4 (Evening) · Jul 4, 2026
Day 5 · Jul 9, 2026
Day 6 · Jul 10, 2026
Day 7 · Jul 13, 2026
Day 8 · Jul 16, 2026
Day 9 · Jul 24, 2026
Day 10 · Aug 2, 2026
Hermes Day 2 · Sep 28, 2026
Hermes Day 6 · Oct 7, 2026
The 7-Day Curriculum
Day 1: Intro to LLMs and Hermes
Fri, Sep 25
Talk only, no lab — the big picture on LLMs and why Hermes Agent is our tool.
Day 2: Hermes Fundamentals
Mon, Sep 28
Getting Hermes Agent running against our local LLMs on real hardware.
Day 3: LLM Routing with Hermes
Wed, Sep 30
Routing requests across multiple local models based on the task.
Day 4: RAG with Hermes
Fri, Oct 2
Grounding Hermes Agent with real data instead of letting it guess.
Day 5: MCPs for Hermes
Mon, Oct 5
Connecting Hermes Agent to external systems and tools over MCP.
Day 6: Tool Calling & Agent Loops
Wed, Oct 7
How Hermes calls a tool, reads the result, and loops until the task is done.
Day 7: Deploy a Production Agent
Fri, Oct 9
Capstone: ship a Hermes agent that keeps working for you 24x7.
Learning on Real Hardware
Three months ago, following Sanjay Jayaram's vision, we purchased a DGX Spark Supercomputerwith a Blackwell GPU and powered it on here in Calgary. Sanjay also picked up a powerful Apple Mac Mini for local AI research after interning at Apple in Cupertino. We'll set up and demo our AI research on both machines live during this course, and Sanjay will join some evenings to share what he's learned.
Powered by the NVIDIA® GB10 Grace Superchip — capable of running a single 200-billion parameter model, or multiple 30-billion parameter LLMs at once.
Ready to Start?
Hands-On. Real Infrastructure. Real Agents.
By the end, you'll have deployed a working Hermes agent — your own digital agent, working and learning for you 24x7.
- ✓ Starting Fri, Sep 25, 2026 — Mon–Wed–Fri, 6:00–7:00 PM MST
- ✓ 5:00–6:00 PM PST · 7:00–8:00 PM EST · 7:30–8:30 AM IST (next day)
- ✓ Live, hands-on, instructor-led
- ✓ Remote access to a DGX Spark supercomputer and Mac Mini
- ✓ 7 sessions, completely free, open to everyone
Want to join or have any other questions? Email jayaram.linux@gmail.com
Starting this Friday — let's commit to learning, building, and shipping real agents together. 🧠