Skip to content
HUIAHUB

ARahim3/DigUp

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.

Metrics updated Emerging
View on GitHub (opens in a new tab)

GitHub metrics

Stars
1.5K
growth after 7 days of data
Forks
102
30-day growth
—
Open issues
30

The chart appears once the repository has been checked on two or more days.

What it does

DigUp is a free macOS menu bar app that searches the files on your Mac by what is in them, using Google DeepMind's EmbeddingGemma 2 model running locally.

You pick the folders it may read. DigUp then indexes pictures, screenshots, PDFs, documents, audio recordings and videos, and you find things by typing a plain description. A hit in a video or recording opens at the matching moment, and a PDF hit opens at the page. Exact strings such as invoice numbers and error codes are matched too, including text that Apple's Vision framework reads from screenshots. Code search is a separate index you switch on yourself: queries start with code: and results open at the line in editors such as Zed, VS Code, Cursor and Xcode.

The README says nothing you index leaves the Mac. The app goes online to download the model once (865 MB) and for a daily update check that can be turned off, and it has no account and no telemetry. Internally it runs EmbeddingGemma 2 on llama.cpp with Metal and keeps vectors plus a keyword index in one SQLite file. It needs an Apple Silicon Mac on macOS 14 or later. The latest release is DigUp 0.6.0.

Why it matters

Finding a file usually means remembering its name or a word inside it. DigUp lets a plain description find a photo, a minute of a podcast or a clause in a scanned PDF, because EmbeddingGemma 2 places text, images, audio and video in one shared space. Indexing and search both run on the Mac, so personal files stay on the machine, and the same search box can cover code once that index is switched on.

Main features

  • Searches photos, screenshots, PDFs, documents, audio and video by plain description
  • Opens video and audio results at the matching moment
  • Matches exact strings such as error codes, including text inside screenshots
  • Cross-language search, for example an English query finding a Bengali or Arabic note
  • Opt-in code search with a `code:` prefix that opens results in your editor
  • Shortcut ⇧⌘Space opens the search panel from any app
  • Reads PDFs page by page, up to 5,000 pages per file
  • Menu bar controls to check, pause or configure indexing

Who it's for

  • Mac users with large folders of photos, screenshots, PDFs and recordings
  • People who need to find a moment inside long audio or video files
  • Developers who want meaning-based search across their own code projects
  • Anyone who wants file search that works without a cloud account

Strengths

  • Indexing and search run on the Mac, and the README states there is no account and no telemetry.
  • One search box covers images, documents, audio, video and, if enabled, code.
  • It never reads keys, certificates, password files or ~/.ssh, and it never changes or uploads files.
  • MIT licensed, with source, tests and an evals folder in the repository.

Limitations

  • Mac only: it needs Apple Silicon and macOS 14 or later.
  • The first indexing pass can take about an hour for a big Downloads folder.
  • The README says its ranking evaluations cover only English, Bengali and Arabic.
  • Exact-word matching does not split languages written without spaces, such as Chinese, Japanese and Thai.

Getting started

Requirements: Apple Silicon Mac with macOS 14 or later, plus a one-time 865 MB model download.

Always follow the official instructions in the README on GitHub. This overview is our summary, not a copy.

Sources