Loading...
Insights on AI, development & automation. Pick a sticky note!
An honest breakdown of running LLMs locally with Ollama versus using OpenRouter's cloud API. Real pricing, real models, and which approach saves you money based on your usage.
A step-by-step guide to configuring Continue.dev — the open-source AI coding assistant — to work with your local Ollama instance for completely private, offline code generation.
Hermes 3 by Nous Research is one of the best open models for function calling and tool use. Learn how to run it locally on Windows, macOS, or Linux using Ollama — no WSL required.
New to local AI? This beginner-friendly guide walks you through installing Ollama, downloading your first model, and chatting with an LLM that runs entirely on your computer — no cloud required.
Learn how to deploy Hermes Agent — an AI agent framework — on Windows using WSL, connect it to your local Ollama instance, and secure it with API key authentication.
We migrated our own website from Vite to Next.js 14 App Router. Here is everything we learned about static exports, Tailwind v4 configuration, and avoiding common pitfalls.
Cloud AI APIs are convenient but expensive and opaque. Here is why running Llama, DeepSeek, and Qwen locally via Ollama is becoming the default for serious developers and enterprises.
From Wise Technologies to Notion, hand-drawn, sketchbook-style interfaces are everywhere. Here is why this anti-design movement resonates with users and how to implement it.