#4141st of 49 in Desktop AI apps

digup

Desktop app that searches local files by meaning across text, images, audio and video

Stars
6.4k
License
MIT
Last commit
Oct 2026
Last release
Oct 2026
Language
Swift
Stars, last 5 weeks+6,365
6 Oct 2026: 8 stars13 Oct 2026: 2,827 stars20 Oct 2026: 5,254 stars27 Oct 2026: 5,928 stars3 Nov 2026: 6,209 stars10 Nov 2026: 6,373 stars

8 on 6 Oct 20266,373 on 10 Nov 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

DigUp indexes folders you choose (images, PDFs, documents, spreadsheets, audio, video, optionally code) using EmbeddingGemma 2 run through llama.cpp, and stores vectors plus a keyword index in one SQLite file. A global shortcut opens a search panel that ranks by meaning and exact words, then opens PDFs at the page and media at the moment. Indexing and search run locally; the network is used only for the model download and update checks.

Who it is for: People who want private semantic search of their own files

Strengths

  • One shared embedding space lets a text query match images, PDF pages, audio and video frames
  • Exact-string boost finds invoice numbers and error codes alongside semantic matches
  • Opens results at the PDF page, media timestamp or code line in your editor
  • No account or telemetry; files are only read, never modified or uploaded

Weaknesses

  • Mac build needs Apple Silicon and macOS 14+; Windows and Linux builds are beta
  • Screenshot text recognition works only on macOS; legacy .doc, RAW and SVG are Mac-only
  • CPU-only first index is slow: about 5 seconds per picture on a 2017 Core i5
  • Initial 865 MB model download; Windows installer is unsigned

What it needs

  • GPU optional
  • Needs llama.cpp, SQLite, EmbeddingGemma 2 (865 MB download)
  • Models: EmbeddingGemma 2 (8-bit GGUF)

Quick answers

Is digup open source?

Yes. Its code is on GitHub under the MIT license.

Does digup need a GPU?

No. It runs on a CPU and can use a GPU when you have one.

Also in Desktop AI apps

See all 49
Also in Desktop AI apps
RankProjectScore
1cherry-studioDesktop client for chatting with many LLM providers, with agents and knowledge bases53.4k stars+1,124 (+2.1%) in 30 daysAGPL-3.092 out of 100
2dsh-desktopNative Windows and macOS desktop client for DeepSeek Harness, built on plugins35.7k stars+5,734 (+19%) in 30 daysMIT90 out of 100
3screenpipeRecords screen and audio locally, makes it searchable for you and your agents22.3k stars+481 (+2.2%) in 30 dayscustom license90 out of 100
#4prompt-optimizerPrompt rewriting and testing tool for web, desktop, Chrome and MCP Live demo ↗ (opens in a new tab)41.2k stars+3,703 (+9.9%) in 30 dayscustom license86 out of 100
#5aionuiDesktop and WebUI app that runs a built-in agent plus external CLI agents34.2k stars+923 (+2.8%) in 30 daysApache-2.086 out of 100