video1.0<iframe src="https://www.loom.com/embed/52ebaa2e8642464488e4ccfc5b1d9211" frameborder="0" width="1152" height="864" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>8641152Loomhttps://www.loom.com8641152https://cdn.loom.com/sessions/thumbnails/52ebaa2e8642464488e4ccfc5b1d9211-57ccce60ba639dbf.gif221.366This Loom introduces StinkerPilot and explains why the author prefers running it locally. The speaker discusses avoiding cloud APIs due to security concerns and personal data privacy, along with cost savings, while still enabling day to day AI tasks. StinkerPilot can explain code and scripts, help write commands by voice prompting, and support question answering across the author’s own knowledge sources like notes stored in local systems, databases, and tools such as Bell nodes and OpsGenie. The setup uses three AI engines, including one for chat summarization using a 2.5 model, plus speech to text options like Moonshine and Kokoro, and it runs on a MacBook Air with 8GB of RAM.