AI
Practical AI workflows, local models, coding agents, automation, model serving, and infrastructure notes focused on real-world use and privacy.
MCP 2026-07-28 Migration Lab: Stateless Core, Auth, and What BreaksNew!!
A practical MCP migration lab for the 2026-07-28 protocol revision: stateless behavior, routing headers, auth checks, cache hints, approvals, tasks, and rollback.
Minimum Viable Evals for Technical AI WorkflowsNew!!
A practical AI evals guide for testing prompts, RAG, coding assistants, config review, assertions, Ragas, promptfoo, and regression checks.
Open WebUI Security Baseline: Patch, Isolate, And Test Tool PermissionsNew!!
A documentation-backed, testable runbook for Open WebUI Security Baseline: Patch, Isolate, And Test Tool Permissions, with safe defaults, validation evidence, failure modes, rollback, and publication-day checks.
Nemotron and Agentic Local AI
A practical guide to NVIDIA Nemotron models and agentic local AI: what a homelab can run, what needs bigger GPUs, and how to keep tools bounded and logged.
Local Coding Assistants: Codex CLI, Continue, Aider, and OpenHands
A noob-friendly guide to choosing and safely using AI coding assistants in a local homelab, including Codex CLI, Continue, Aider, OpenHands, local models, hosted models, Git safety, and task scoping.
Build a Private RAG Box for Network Docs
A private RAG guide for network documentation, configs, diagrams, NetBox exports, runbooks, embeddings, vector search, citations, and evals.
Adding RAG: Chat with Documents Locally
A beginner-friendly guide to local document chat, embeddings, vector databases, Open WebUI knowledge bases, privacy, and common RAG mistakes.
Local AI Hardware Sizing: CPU, NPU, GPU, RAM, and VRAM
A local AI hardware sizing guide explaining model memory, quantization, KV cache, CPU-only use, NPUs, GPUs, RAM, VRAM, and upgrade tiers.
Home AI Hardware Levels: A Beginner's Guide to the PC You Need
A plain-English guide to choosing hardware for a home AI setup, from using an old PC to building a serious GPU workstation.
Local AI Models Explained: Gemma, Llama, Qwen, Nemotron, Phi, DeepSeek, and More
A noob-friendly guide to local AI model families, model size, VRAM, quantization, RAG, coding models, vision models, and how to choose what to run at home.