-
Owning Your Agent, Part 2: Local Agents in the Wild — Using Hermes to Upgrade My WHOOP
Before We Begin Welcome back. This is a follow-up from our part 1 agent poast I did a few months ago. A lot has changed since the first agentic post that I published. I built a new AI cluster, my v2 machine, and it’s juiced up big time compared to the previous machine, when I…
-
Go Big or Go Home, Part 3: Testing A LOT of models on the New GPU Cluster
Two RTX 3090s, 128 GB of ECC memory, and four open-weight models: testing hybrid inference, long context, MTP, agents, and real applications.
-
Go Big or Go Home, Part 2: Commissioning the new GPU cluster
Before We Try to Break It Part 1 covered why I rebuilt my local AI system around WRX90, a Threadripper PRO 9955WX, 128 GB of eight-channel ECC RDIMM, two RTX 3090 Founders Edition cards, Ubuntu, air cooling, and hardware-level remote management. When almost $11,000 in tracked hardware acquisition value sits inside one case, “it boots”…
-
Go Big or Go Home, Part 1: My New AI Cluster
Before We Start I built a new local AI server. It is fully operational, and I have the benchmark data—and the results from running some seriously large open-source models—to prove it. Local AI rigs exploded in popularity in 2026 alongside the growing demand for models that people can run on their own hardware. Unfortunately, the…
-
Were so freaking Back (even though we never left)
Howdy yall. I’ve been a bit MIA since the start of summer. Life was (and still is) operating at 2x speed. I wanted to provide a proof-of-life poast so that you could see that I am indeed alive and well, and that I am “locking in,” as the young lads say these days. I just…
-
Owning Your Agent part 1: Local Agentic Work with Hermes on Dual RTX 3090s
“Never send a human to do a machine’s job.” – Agent Smith, The Matrix (1999) You fire up your machine and stare aimlessly into the terminal — “or whatever ‘insert AI company name’ app you opened today” — and your reflection stares back at you from the screen. You’re waiting on Claude Code. Again. The…
-
Year of the Fire Horse, Year of the Agent: A Prelude to My Agentic Research
I just wrapped up the first research module on local agentic AI and I have a lot to say. Before I start publishing my work on agents, I wanted to drop this post as a warmup (and a warning). We are progressing rapidly with local AI. As of 2026, we fast-tracked our way via model…
-
48 GB of VRAM and a Dream – Part 2: The AI Bubble in My Parts List
I’m in the middle of building my second GPU cluster, and I’m losing hair (literally) staring at current RAM, SSD and GPU prices. They are not what they were 18 months ago. In Part 1 of this series I walked through the V1 build — a dual RTX 3090, 48 GB VRAM rig that came…
-
48 GB of VRAM and a Dream – Part 1: The Build
A quick note before you read: In light of the ongoing AI bubble, I have provided a full cost breakdown of all parts of when I bought them. I am currently in the process of building a new AI cluster — a big upgrade . When it’s done, I will post about it. I hope…
-
The Memory Must Flow: Why I Built a Dune-Themed CLI to Analyze Local AI Memory on Apple Silicon
“Thou shalt not make a machine in the likeness of a human mind.” — Orange Catholic Bible, Dune THE DUNE CONNECTION – INSPIRATION FOR MELANGE I was gifted all six Dune books years ago as a Christmas gift. They traveled with me unread through three apartments, collecting dust. At the start of 2026, I finally…