PCB-Labeller-Demo
May 4, 2026 · View on GitHub
Proof of concept: using AI to annotate PCB (and other hardware) images and help the user plan a project, coupled with light research assistance.
Idea
Point a vision-capable model at a photo of a PCB (or breadboard, module, or other piece of hardware) and have it:
- Identify visible components, pin headers, ICs, connectors, silkscreen markings.
- Produce an annotated overlay (boxes / labels / callouts) on the original image.
- Suggest next steps for the user's stated project goal — wiring, missing parts, datasheets to look up, likely pitfalls.
- Pull in reference material (datasheets, pinouts, similar projects) to ground the suggestions.
Status
POC / scratchpad. Not a finished tool.
Planned pieces
inputs/— sample PCB photos to test againstoutputs/— annotated images + per-image notesprompts/— prompt templates for the labelling + planning passesscripts/— glue code (image annotation, research lookups)
Why
Hands-on hardware work benefits from a "second pair of eyes" that can read silkscreen, recognise common parts, and surface relevant docs without breaking the user's flow.