Breaking

Google Releases DigUp, Free macOS Semantic Search App Powered by EmbeddingGemma 2

October 13, 2026 at 12:27 EDT

Foundation Models
Open Source
Software Dev & Coding

Google Gemma has released DigUp, an open-source semantic search application that lets Mac users find files by describing their contents in natural language rather than searching by filename. The free, MIT-licensed menu bar app runs entirely on-device using Google DeepMind's EmbeddingGemma 2, a 740-million-parameter multimodal embedding model that converts text, images, audio, and video into a shared 768-dimensional vector space.

October 2026 · Google DeepMind

DigUp: Semantic Search Comes to Mac

Free open-source app powered by EmbeddingGemma 2 enables local, multimodal file search across images, video, audio, PDFs, and code—no cloud upload required.

740M

Parameters

567

MB RAM (full)

865

MB Download

768

Vector dims

What Makes DigUp Different

Cross-modal search: Text queries find video moments, images find PDFs, audio finds documents—all in one unified vector space.
Runs offline: No cloud upload, no subscriptions, no internet required after initial model download.
MIT licensed: Free, open-source app available on GitHub (2,200+ stars).
Language support: Semantic search in 100+ languages; OCR in ~25 languages via Apple Vision.

Primary Strengths

Code search (+9.92 pts)
Privacy-first design
Instant local indexing

Practical Limits

Apple Silicon only (macOS 14+)
Video indexing: 0.2 embeds/min
Text search trails v1 marginally

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.