09-11, 13:00–13:20 (Europe/Berlin), Main KiCon Presentation Space
This talk introduces a new, "dead-simple" paradigm for KiCad libraries, powered by AmpereBrain. We will demonstrate a workflow where managing complex, version-controlled libraries becomes as easy as dragging and dropping a file. AmpereBrain automates the entire lifecycle: it ingests component files, organizes them into a Git-backed repository, and automatically searches for, downloads, and processes datasheets. We will showcase how this system creates an intelligent, queryable component database by loading datasheet information into a Large Language Model (LLM), allowing you to ask complex questions in natural language.
This session is a practical demonstration of how to eliminate library management friction and build an intelligent, automated component ecosystem. We will move beyond theory and show you a system that works today.
The talk will cover:
The "One-Click" Library Setup (5 min): We'll start by configuring a project's library system by linking it to a remote Git repository with a single command. This sets the stage for a robust, version-controlled, and shareable library.
Drag-and-Drop Component Ingestion (5 min): A live demo of the core workflow. We will drag a component .zip file into AmpereBrain, and you will see it automatically:
Extract the symbol, footprint, and 3D model.
Place them into the correct directory structure within the local Git repository and edit the paths accordingly.
Commit the new component with a descriptive message and push it to the remote library.
The Intelligent Datasheet Engine (5 min): We'll showcase the multi-tiered datasheet system in action. When a component is added or a project is loaded, AmpereBrain automatically:
Offer to search for the datasheet if one isn't provided.
Downloads and processes the PDF into clean, searchable Markdown for local and custom components.
Creates a direct link for global components to save space.
Query Your Schematics or Library with an LLM (5 min): We will demonstrate how the processed datasheets are fed to a local Large Language Model. You'll see us ask questions directly like:
"What is the maximum operating temperature for U1?"
"Find me a capacitor in my library with a value between 1uF and 10uF and a voltage rating of at least 25V."
"Does this op-amp have a rail-to-rail output?"
This talk is for every KiCad user who wants to spend less time managing files and more time designing. You will leave with a clear understanding of how to build a smarter, more automated library workflow.
Founder of the StepUp companies, building wearables. Following closely the AI revolution.