When most of us think about Artificial Intelligence, we picture a single, all-knowing brain. We type a question into a chatbot, and a massive, incredibly smart engine spits out an answer. It’s easy to assume that the secret to a great AI application is simply finding the biggest, smartest, most powerful AI model on the…
The artificial intelligence industry has experienced exponential growth in model capabilities over the past few years. As we have moved from models with billions of parameters to systems containing hundreds of billions of parameters, while expanding context windows into the millions of tokens, a new challenge has emerged: token efficiency. Every token carries a cost…
Time to revisit The Rise of the Enterprise Token Broker blog post The AI Gateway—the centralized “Token Broker”. I’ll be honest: writing this post feels a little like breaking up with someone you genuinely like. OpenRouter has been part of my daily workflow for two and a half years. It solved a real problem, it…
Imagine a highly skilled, tireless digital employee sitting next to you. You do not need to teach it Python, you do not need to show it how to navigate APIs, and you do not need to write a single line of code to get it to build a workflow. You just talk to it. This…
I get asked all the time: “What are you actually using for your AI Lab?” To answer that, I wanted to provide an update on how I’m building, testing, and deploying. But first, a little background. I’m a technology consultant and services principal, and I’ve been developing custom software since I was 15. I’ve been deep…
How I Bypassed Ollama and LM studio Limitations on my Ryzen AI NPU to Hit 50+ TPS If you recently purchased a modern AI-PC, you bought into a promising vision: a dedicated, cutting-edge Neural Processing Unit (NPU) sitting right inside your silicon, designed to stream large language models (LLMs) smoothly without draining your battery or…
The next generation of AI-capable laptops is being shaped by a new set of requirements. Users increasingly expect thin-and-light systems to handle demanding workloads such as local AI assistants, content creation, software development, and advanced productivity applications without sacrificing battery life or portability. Intel’s upcoming Panther Lake platform, expected to launch as part of the…
Here is your comprehensive, fully revised, and complete blog post. For years, the discourse around Artificial Intelligence was dominated by the idea of the “Prompt Engineer”—the person who spent their time hunting for the exact combination of words, trigger phrases, and formatting tricks to coax a brittle model into producing a decent answer. If you…
Nvidia’s dominance in the AI hardware market is not solely due to its high-performance GPUs. The company’s real strength lies in its comprehensive ecosystem, centered around its proprietary Compute Unified Device Architecture (CUDA). Over the past decade, CUDA has evolved from a programming framework into the foundation of modern AI development, creating a powerful network…
The workplace is moving beyond chatbots and into a new category of software: digital coworkers. These are AI systems that do more than answer questions; they can execute background tasks, manage files, coordinate workflows, and keep working on complex jobs with less step-by-step prompting. What makes this shift important is simple: instead of asking AI…
There was a time when choosing an LLM provider was simple: you grabbed an OpenAI API key, plugged it into your environment variables, and started building. But the landscape has fundamentally shifted. Today, building production-ready AI agents or managing complex enterprise workflows requires navigating a sprawling, fragmented ecosystem. On any given day, your architecture might…
As enterprises scale their AI operations from experimental “playgrounds” to full-scale agentic workflows, a new bottleneck has emerged: Token Controlling and API Key Chaos. With teams of 6–10 developers or automated agents hitting multiple providers (OpenAI, Anthropic, Gemini) and local servers simultaneously, managing individual accounts is no longer viable. Enter the AI Gateway—the centralized “Token…
Back in 2024 I wrote a blog post: How Much Does It Cost to Operate AI ChatBots? As we move into the new era of the token economy, the conversations, about tokens costs and power are very much part of the story. A useful model must account for real model pricing, utilization, infrastructure, performance, and…
Starting with the May 2026 security update, any developer can register AI agents via Windows.UI.Shell.Tasks API to appear alongside Copilot. Users invoke with “@” in search, monitor chain-of-thought via hover. This positions Windows as the OS for agents, not just AI features. In a move bigger than another Copilot tweak, Microsoft is turning Windows 11…
The narrative around artificial intelligence has long been dominated by bigger equals better. Models with trillions of parameters, trained on internet-scale datasets, powered by massive GPU clusters—these were the benchmarks of progress. But something interesting is happening at the other end of the spectrum. Small models—measured in billions, not trillions of parameters—are proving they can…
To learn more about Local AI topics, check out related posts in the Local AI Series In the landscape of Generative AI, Retrieval-Augmented Generation (RAG), and semantic search systems, vector databases have shifted from niche machine learning tooling to core backend infrastructure. At the center of almost every architectural evaluation sits a classic engineering dilemma: Should…
For the last few months, I’ve been working on a new book series called AI: Don’t Just Chat. I wrote it because the pace of AI has become exhausting for a lot of people. The tools change constantly. The advice shifts. What worked a few months ago can already feel outdated. Even people who are deep…
To learn more about Local AI topics, check out related posts in the Local AI Series If you are using Agent Zero and suddenly see this error, you are not alone: “`text ValueError: Could not find document for id 6oqX1vwBxV, got ID 6oqX1vwBxV not found. “` This problem can show up repeatedly, sometimes with different document…
I just posted yesterday Local AI Sovereignty: Deploying Ollama, Gemma 4, OpenWebUI, and n8n and I used Gemma 4 locally on Ollama. Someone asked me a good question: What and Why Gemma 4 Large language models (LLMs) have rapidly evolved from research concepts into foundational tools for modern work. Gemma 4 represents one of the…
I just posted yesterday Local AI Sovereignty: Deploying Ollama, Gemma 4, OpenWebUI, and n8n and I used Gemma 4 locally on Ollama. Someone asked me a good question: What size computer (Windows PC) do I need tor it? What size computer do you need for Gemma 4? Google’s April 2026 release of Gemma 4 changed…
With 64GB of RAM and the latest Ryzen AI silicon, you are no longer a mere consumer of AI—you are a host. This setup leverages AMD’s XDNA architecture to run Gemma 4 and / or and Qwen 3.5 locally, ensuring your data never leaves your machine while providing a professional-grade automation suite via Docker. This…
AI agents are moving fast from demos to real workflows. Two names that keep coming up are OpenClaw and NemoClaw, and they are often mentioned together because NemoClaw is built as a security-focused layer around OpenClaw. What is OpenClaw? OpenClaw is an open-source AI agent framework that runs on your own hardware and connects AI…
Architecting the Ultimate Solo AI Partner for Client Acquisition As a technical solopreneur running an independent web infrastructure shop, you manage a fragile, complex balance. On any given day, you are the lead system architect tracking PHP memory drops, the front-end developer polishing complex JavaScript loops, the security engineer hardening WordPress installations, and the helpdesk…
OpenClaw (formerly known as Clawdbot, Moltbot). It’s remarkable how quickly a tool can become indispensable once you integrate it into your daily routine. I still remember my first week using it—curiously has taken the productivity world by storm, and for good reason! With its impressive range of features, it has captured the attention of countless…
When I first started experimenting with Agent Zero, I wanted to keep things totally “temporary” and isolated from my own data. My mindset was simple: I didn’t want the Docker container saving any clutter to my computer. I wanted it to start fresh every time. For a few days, this worked well. Agent Zero was…
AI development is rapidly shifting from cloud-first workflows to hybrid and fully local environments. Rising API costs, data privacy concerns, and the demand for low-latency inference are pushing organizations and developers to rethink where their models run. The Dell Pro Max with GB10 Desktop, enters this space as a compact, desk-side AI workstation designed to…
For months, I’ve been refining my local AI lab. I had the hardware dialed in—my AMD Ryzen AI processor, 128GB of RAM, running Ollama and Open WebUI like a dream. But I kept hitting the “invisible wall.” Every time I asked my local agents for the morning’s technical headlines or a deep dive into a…
I started an experiment today… We’ve all seen the flashy trading bots promising “1000% returns,” but usually, those come with a hefty subscription fee and a black box where your data goes to die. If you’re already running a local agent (via Ollama, LM Studio, AgentZero or a custom build one), you’re sitting on untapped…
The buzz around Artificial Intelligence is everywhere, but the conversation is shifting. We are moving away from “chatbots in a browser” and toward Local AI Agents—personalized assistants that live on your device and work for your individual productivity. As we enter 2026, the winner in this space isn’t just the company with the smartest code;…
I written a few posts about tokens in the past, but as a follow up to my post: LLM Usage Stats on My Development Spree where I spent about $120 during a 45 day period to code using Kilo Code I got curious and dove a little bit more into what the cost of what…
This blog post discusses the author’s journey into the world of local AI and agentic experiments. Starting with “vibe coding” and coding agents last year, the author then discovered AgentZero, a local, self-contained AI agent in a Docker container, which allowed for cloud-independent experimentation. In January, the author moved on to ClawdBot (now OpenClaw), another…
Apple’s Unified Memory has been a game-changer for Local AI and Everyone Else is Catching Up.. The buzz around Artificial Intelligence is everywhere, and one of the most exciting frontiers is “Local AI” – running powerful AI models directly on your device, without sending your data to the cloud. If you’ve been following the developments,…
Let your AI assistant send emails on your behalf — in minutes. Agent Zero is a powerful AI framework that can automate tasks, run code, browse the web, and much more. But one capability many users overlook is email sending — and it’s surprisingly easy to set up. This guide walks you through enabling Gmail-based…
OpenClaw was first introduced in November 2025 by Austrian developer Peter Steinberger, who originally published it under the name Clawdbot before later rebranding it. Since then, it has grown into one of the fastest-rising open-source AI agent projects, with coverage reporting massive GitHub growth, heavy traffic, and broad developer interest. What is OpenClaw? OpenClaw is…
When I first started experimenting with Agent Zero, my goal was to keep everything temporary and isolated. I did not want the container leaving clutter on my computer, and I wanted a setup that could start fresh every time. For the first few days, that worked perfectly. Agent Zero was still new to me, and…
You have AgentZero installed and running. Now what? Before you start delegating tasks and building automated workflows, it helps to understand what you actually installed and where everything lives. This guide walks through the file structure, explains how projects work, and shows you where to find the documentation you will inevitably need. What You Actually…
Agent Zero is an open-source AI agent framework that lets users run autonomous AI assistants in their own environment, often inside Docker for isolation and portability. It is designed for tasks like coding, web browsing, research, planning, and tool use, giving it a broader role than a simple chatbot. When It Became Available Agent Zero…
Choosing the right LLM isn’t just about performance anymore—it’s about the economics of scale. As we enter 2026, the cost of intelligence is dropping, but the volume of tokens being “burned” is skyrocketing. If you are building an AI-powered application today, understanding the nuances of token consumption is the difference between a profitable product and…
The world of AI development is evolving at breakneck speed, and with it, the hardware designed to fuel its progress. Enter the Dell Pro Max with GB10 Desktop, a fascinating piece of kit that’s carving out a unique niche in the market. This compact AI workstation aims to bring data-center-level performance directly to your desk….
Back in 2024 I wrote a blog post: How Much Does It Cost to Operate AI ChatBots? Today I am updating it with a bit more knowledge and information and pointing you to the calcultor I have created and use to explain this concept. Introduction Building a Retrieval-Augmented Generation (RAG) chatbot is an exciting venture,…
As a follow up to my How to Host Multiple Public Websites on Your Windows PC a few months bac, I am writing this one If you want to move away from expensive AI subscriptions and bring your data back home, building a local AI home lab is the answer. Today, I’m documenting how I…
To understand how to build a truly effective AI agent, you must first acknowledge the core constraint of the Large Language Model (LLM) itself. “LLMs are ‘frozen’ in time as of their training data (The Training Cut-off).” Think of an LLM as a massive, read-only database. During its “training” phase, it reads a significant portion…
When you hear about the latest large language models (LLMs)—like GPT-4, Claude, or Gemini—it’s easy to feel overwhelmed by their sheer scale. These models contain billions, sometimes trillions, of parameters. This incredible size is what gives them their broad capabilities—from writing code and summarizing texts to answering complex questions and creating poetry. But that scale…
Companion post to my blog Guide to Local AI: Picking a PC in September 2025 A few Videos I have found interesting in my research AMD Ryzeon AI PRO MAX Best AI Mini PC Deep Dives into Nvidia’s DGX Spark GB10 Video 2 Building AI Rigs for Rent (salad.com) Building an AI MAchine!(with MicroCenter’s help)…
I’m a freelance developer (well, kind of semi-professional, “Pro-am coder“, “Weekend and late nights warrior developer“) who loves to vibe code with AI. My go-to teammates are tools like Gemini and Claude, which I rely on for code generation and solving complex problems. It’s an amazing workflow—at least until the moment the AI drops a…
The future of AI isn’t just in the cloud; it’s right on your desktop. Running AI models locally offers unparalleled privacy, speed, and creative freedom. But with so many options from AMD, Intel, and Apple, how do you choose the best “Local AI PC” for you? Let’s break down the leading architectures and what they…
Coming from a personal experience, this was confusing, and it took me a while to figure out. If you’ve are looking into running AI locally, upgrading a workstation, or even just buying a powerful GPU, you’ve probably run into NVIDIA’s confusing lineup: the old Quadro cards, the modern RTX A-Series, and the consumer-focused GeForce RTX….
Overview This is the executive summary from the Jorge Pereira’s point-of-view / whitepaper on the Student Lab for AI Learning which outlines the potential strategy to establishment of a Student AI Lab designed as a collaborative learning environment where students and staff explore artificial intelligence technologies spanning foundational principles through advanced applications. The proposed lab…
In the past year alone, I’ve tested MANY AI tools, built over a dozen “client” projects, mentor many on how to use AI, and saved many of hours through automation—all because I chose experimentation over endless research. My mantra is simple: to keep up with AI, I embrace a culture of experimentation, testing, and side…
Originally posted on JorgeTechBits Substack My mantra is simple: to keep up with AI, I embrace a culture of experimentation, testing, and side projects. I prefer DOING over merely listening, reading, or watching. (Though I must confess, I do spend a fair amount of time binge-watching YouTube tutorials!) This hands-on approach helps me maintain a…
Ollama, Open WebUI and n8n on Windows Hosting your own AI models is no longer just for Linux gurus. With Docker Desktop on Windows, you can run a professional-grade automation and chat suite—n8n, Ollama, and Open WebUI—all on your own hardware. In this guide, we will set up a “Generic” configuration that makes it easy…
Copilot+ PCs vs AI PCs: What’s the Difference—and Why It Matters The personal computer is going through its biggest transformation in decades. With artificial intelligence moving from the cloud directly onto devices, terms like “AI PC” and “Copilot+ PC” are starting to show up everywhere. While they may sound interchangeable, they’re not the same—and understanding…
When I initially installed Ollama and Open WebUI I installed it in two separate images (Did not know any better!). It worked well for what I wanted but then as I played with other applications, I started to have too many containers in Docker, so I looked for a way to consolidate images. ( Not…
You don’t need a supercomputer to run AI models, but the right software makes all the difference. Here are some options to get you started on your local AI journey. AI is no longer exclusive to data centers and cloud services. With the right software and a decent PC, you can run powerful AI models…
See Also: AI on the PC: A New Era in Personal Computing and Local AI Series In the ever-evolving landscape of technology, various processing units are at the heart of our devices. Understanding these components helps us appreciate their unique capabilities and the specific tasks they’re built to handle. This article explores CPUs, GPUs, NPUs,…
Large Language Models (LLMs) have revolutionized the field of natural language processing and artificial intelligence. These powerful models enable applications like language translation, text summarization, and content generation. The world of Large Language Models (LLMs) can be intimidating, especially with the associated costs. However, there are plenty of free and low-cost options available for those…
See 2025-01-13-UPDATE below I am so excited about this technology! I have been using local AI on my Dell Precision Laptop. It is SLOW but the capabilities and possibilities are incredible. The use of AI on my local machine will change the way I work,. Incredible.. Copilot+ PCs from Microsoft In May 2024, Microsoft has…
