Build a local dashboard for indexing and labeling
Wrap indexing, labeling, threshold tuning and export in one local browser page, and handle the threading traps that come with it.
How to run AI models on your own machine and your own files, with no cloud and no API bill.
Every guide explains why each step works, names the errors you will actually hit, and says where the approach stops working. Numbers are marked as measured or estimate, never blurred together.
Three things this site covers
findFinding things in your own filesSearch your own photos, documents and archives with models that run locally.6 guidesrunRunning models locallyGet a model onto your machine, running offline, at a speed you can live with.1 guideteachMaking models do what you wantCorrect a model that is close but wrong, without a training run or a GPU bill.2 guides
Recent guides
All guidesTeach it what you want with a correction loop
Fit a classifier on frozen embeddings in about a second, correct the cases it is least sure about, and know when to stop.
Every error we hit building this, and the fix
The literal error messages from building a local image search tool, why each happened, and what fixed it.
Find people in your photos without labeling anything
Why CLIP cannot tell people apart, what to use instead, and how clustering discovers everyone in your library with almost no input.
Find anything in your own photo library, offline
A seven-part series on building a private image search tool that learns which photos you actually want.
Search Your Own Photo Library Offline With CLIP, Start to Finish
Index a folder of photos with CLIP and search it by typing what you remember seeing, with no cloud and no API key.