Fresh/Brewed

A mild fall
Getting Started with LM Studio

Getting Started with LM Studio

Something other than Ollama

The first thing that caught me up going to lmstudio.ai was the default download is an AppImage file but you can use the dropdown to pick a .deb instead Next, I want to stop Ollama before moving on to LM Studio isaac@isaac-G707:~/Workspaces/fbsnew$ ollama ps NAME ID SIZE PROCESSOR CONTEXT UNTIL isaac@isaac-G707:~/Workspaces/fbsnew$ sudo systemctl stop ollama.service [sudo: authenticate] Password: isaac@isaac-G707:~/Workspaces/fbsnew$ ollama ps Error: could not connect to ollama server, run 'ollama serve' to start it isaac@isaac-G707:~/Workspaces/fbsnew$ I can now install it

OS Apps: OpenGym and Ente Toys

OS Apps: OpenGym and Ente Toys

Pump you up and then goof off

I’ve had a few Open Source apps in the queue to review as of late. First up, from a Marius post is OpenGym. It can run in docker compose and kubernetes and is a really complete self-hosted workout and health management tool. It has a lot of extras (like ties to trainers, nutrition sites, OAuth endpoints, etc). Second, I was going to dig into an Auth tool by Ente but instead got completely lost in their Toys area. They have more than enough to keep us distracted for a while.

OS Chatbots with n8n and Ollama in GCP

OS Chatbots with n8n and Ollama in GCP

A Chatbot you can control using n8n workflows

I’ve given talks before about n8n and chatbots. I’ve been using n8n for years now and have had a few articles about it. But in almost all cases, I’m running n8n locally in Docker or my local Kubernetes. How hard would it be to pivot to using Cloud Compute? Could we run n8n in Cloud Run, especially as there are now persistent Cloud Run instances? What about GCP Cloud Compute? Could we even run some small LLM models in Ollama without the GPU tax? How would that compare with Gemini API keys or an SA that uses Agent Platform?

OS Harnesses: OpenCode

OS Harnesses: OpenCode

Goal Mode and Model Updates

I dance between Harnesses, I do. I like the big players like Copilot, Claude and Antigravity CLI, but really the up and comers are the ones that catch my attention. I lasted spoke on OpenCode in August of 2025. While I noted it was from sst.dev I didn’t really dig into what SST was (or why one would use it). At that time, I was comparing OpenCode to OllamaCode and Qwen3 Coder Plus (along with the much loved and now defunct Gemini CLI).

OS IaC: Pyinfra

OS IaC: Pyinfra

A Python-based IaC

Recently I gave an Infrastructure as Code (IaC) talk on Open-Source tooling and focused on Ansible and OpenTofu. One of the participants asked me about Pyinfra which I had never heard of before. Pyinfra is fully MIT licensed and seems rather full featured. Today we will get it setup locally, create some basic “deploys” (their word for playbooks), then look at remote deploys before showing how we can create scheduled YAML based pipelines to launch and manage infrastructure with Pyinfra.