DigUp: Local Semantic Search for Mac Built on EmbeddingGemma 2
DigUp is an open-source Mac search app that uses EmbeddingGemma 2 embeddings to find files and their contents locally, without uploading data.
DigUp: Local Semantic Search for Mac Built on EmbeddingGemma 2
A search app for Mac built on Google’s EmbeddingGemma 2 model works much better than the standard Spotlight in macOS.
The app is called DigUp. It can search not only files, but also their contents: PDFs, screenshots, photos, podcasts, and videos.
This is possible thanks to embedding-based search. You do not need to know exact words. You can roughly describe what you are looking for, and the model will find the most relevant result. For example, a query like “where they talk about sleep” can jump straight to the right moment in a podcast.
The model itself is small and open source. It runs locally on the Mac, so your files are not sent anywhere.
This kind of search can be implemented almost anywhere local search is used today.
Why it matters
AnalysisIt shows how small open models can turn local file search into private semantic search, reducing reliance on exact keywords and cloud indexing.
Discuss in community
Share your questions and insights with developers