GitHub - ARahim3/DigUp: Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
Short summary
DigUp is a free, open-source desktop app that lets you search files on your computer by describing what you're looking for in plain language—finding photos, PDFs, videos, and audio by meaning rather than filename. It uses Google DeepMind's EmbeddingGemma 2 model to understand text, images, audio, and video across 100+ languages, and everything runs locally on your machine with no cloud uploads or tracking.
- Searches across multiple file types (images, PDFs, documents, audio, video) in a single query, matching both semantic meaning and exact strings like invoice numbers or error codes
- The 740M-parameter EmbeddingGemma 2 model runs entirely on your computer—all indexing stays local, with only one-time model download and optional daily update checks
- Includes code search that can find functions by what they do ("retry a failed call with backoff") or by name, opening results directly in your editor at the correct line
- Initial indexing takes minutes to hours depending on file volume, then new files become searchable within seconds
Full summary
DigUp is a desktop search tool that indexes your files using Google DeepMind's EmbeddingGemma 2, a 740-million-parameter multimodal model released in October 2026. Instead of searching for exact filenames or keywords, you describe what you're looking for in plain language and it finds matches across photos, videos, PDFs, audio files, and documents. A search for "zebra in a video" jumps to the exact moment a zebra appears; "where they talk about sleep" finds that minute in a podcast; "the clause about pets in the lease" pulls up the right PDF page. The model works across 100+ languages, so an English search can find a note written in Bengali or Arabic. It also matches exact strings like invoice numbers and error codes alongside semantic meaning.
The app runs entirely on your machine—nothing leaves your computer except a one-time 865 MB model download and optional daily update checks. It's free and open source under Apache 2.0. DigUp works on Mac (Apple Silicon, macOS 14+), Windows 10/11 (64-bit), and Linux (Ubuntu 22.04+, Debian 12+, Mint 21+). You pick which folders to index, and the first pass takes anywhere from minutes for a small library to hours for a massive photo collection. After that, new files become searchable within seconds. You activate search from any app with ⇧⌘Space on Mac or Ctrl+Shift+Space on Windows/Linux, and results open at the exact location—PDFs to the page, videos and audio to the timestamp, code to the line in your editor.
For developers, DigUp includes optional code search that understands functions, variable names, and what code does. A search like "code: retry a failed call with backoff" finds the relevant function regardless of its actual name. It indexes source files, notebooks, and repo documentation while skipping vendored code, data files, and anything resembling passwords or keys. On a Mac, indexing a small app takes about 20 seconds; larger projects run around 20 minutes. The tool respects privacy by never reading hidden folders, credentials, or cloud-only files, and you can manually exclude additional folders or file types.