AI Collab Score: 7 / 3

How I used Ubuntu, OpenCV, Ollama, Gemma 3 Vision, and Python to build a local vision pipeline with memory, event filtering, and stability logic.

Most AI vision demos stop at image description.

A webcam captures an image, a vision model analyzes it, and the system prints something like: “A person is sitting at a desk.”

That is useful as a proof of concept, but it does not behave like an agent.

A real vision agent needs more than perception. It needs state. It needs memory. It needs event logic. It needs to know what changed, whether the change matters, and whether the change is stable enough to trust.

That became the goal of this lab.

I built a local AI Vision Agent that starts with a live webcam feed and evolves into a small event-driven vision system. It runs locally on Ubuntu using Python, OpenCV, Ollama, and Gemma 3 Vision.

By the current version, the agent can confirm events like:

• person entered
• person left
• phone appeared
• mug disappeared
• laptop appeared

​The important part is not just that the model can describe what it sees. The important part is the system built around the model that turns raw vision output into confirmed events.

AI Collab Score: 7 / 3

Last year, I documented my first NVIDIA AI Workbench installation on a repurposed workstation. That project was about validating CUDA, cuDNN, PyTorch, and GPU acceleration. It proved that an older workstation could become a capable local AI development platform.

This rebuild had a different purpose.

I did not want to recreate a collection of global Windows installs and hope every framework, runtime, and dependency remained compatible over time. I wanted to build a modular local AI lab that more closely resembles the technical layers enterprise teams must eventually design, secure, operate, and scale.

The result is a lean open-source AI stack built around Windows 11, WSL2, Docker Desktop, Ollama, and Open WebUI.
​
More importantly, it gave me a practical answer to a question many people have:

AI Collab Score: 10 / 2 

​Part of the VCF Automation Series: Tenant-Ready Workflows at Scale

VMware Cloud Foundation 9.0 marks a major leap toward a true private cloud platform—with built-in multi-tenancy, automated provisioning, and extensible workflows via external Orchestrator instances. But there's still one critical gap many platform teams face:

That’s where Red Hat Ansible becomes the missing piece.
This post shows how to integrate Ansible with VCF 9.0 Automation to deliver:

• Full-stack automation from VM to application
• Tenant-scoped workflows via external vRO instances
• Post-deployment actions like patching, agent installation, and OS hardening
• GitOps-friendly, repeatable playbook execution
• RBAC and policy enforcement across tenants

If you're building a cloud platform on VCF 9.0, this integration is not just nice-to-have—it's essential.

Provisioning automation alone does not create a stable platform.
​
I created a companion video to explain how Red Hat Ansible integrates into VMware Cloud Foundation 9.0 as the lifecycle governance layer — enforcing state, validating compliance, and stabilizing Day-2 operations.

Watch the overview below, or continue reading for the full discussion of the architecture.

​VMware Cloud Foundation 5.2.1 brings a suite of enhancements aimed at making lifecycle management more efficient, improving flexibility in cluster upgrades, and preparing your infrastructure for AI and modern apps. If you're running a hybrid environment, or prepping for GPU-enabled workloads, this is a release you’ll want to master.