⬢github Swift · 1.4K ★ +575 since we first saw it · pushed 1 d ago · MIT
ARahim3/DigUp
Search your Mac by what's in your files: photos, PDFs, recordings, videos and code. On-device, built on Google DeepMind's EmbeddingGemma 2.
DigUp is a free, open-source macOS menu bar app that lets you search your files by meaning, not just filenames. Using Google DeepMind's EmbeddingGemma 2 model, it indexes photos, PDFs, videos, recordings, and code entirely on your Apple Silicon Mac, so you can describe what you're looking for in plain words and jump straight to the right photo, video moment, PDF page, or line of code.
Why now: It's trending as a newly released, most-starred repo that builds on Google DeepMind's just-released EmbeddingGemma 2 multimodal embedding model, riding interest in private, on-device semantic search.
Who it is for: Apple Silicon Mac users who want fast, private search across the actual contents of their photos, PDFs, videos, recordings, and code.
embeddinggemmaembeddingsllama-cpplocal-firstmacosmenubar-appmultimodalon-devicesemantic-searchswift
Stars over our 48 snapshots: 814 to 1.4K, since 12 h ago.
Where people talked about it
- ⬢github new repos, most starred 4 min ago
- ⬢github new repos, most starred 8 h ago
API: https://socialmediatrends-api.osmike.com/v1/repos/ARahim3/DigUp