Tools/ARahim3/DigUp

DigUp

Searches your files by what is inside them, not what they are named, with a model that runs on your own Mac, Windows or Linux machine.

5.6k ★+1.4k/wkemergingSwiftMIT License →new this week

The Lens

By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.

Updated Oct 2026

DigUp searches your computer by what's inside your files, not what they're named. Type "a dog on the beach" and it finds the photo; type "the clause about pets in the lease" and it opens the PDF page. It runs Google DeepMind's EmbeddingGemma 2 model on your own machine, and it's free and MIT licensed.

The Mac build (Apple Silicon, macOS 14+) is stable. Windows and Linux are in beta, and the Windows installer still isn't signed. First launch downloads an 865 MB model, then reads the folders you pick: minutes on a Mac, hours for a big photo library on a PC without a good graphics card. Nothing you index leaves the machine. Code search is opt-in.

There's no paid tier, and the model weights are Apache 2.0 too. Solo and small teams: free. Larger teams: free per machine, but every index is personal.

The catch: it's two weeks old. Update the Mac app to 0.6.2, which fixed the battery drain and a high-severity bug that let a copied repo's git settings run a program during code search. A memory runaway on certain PDFs is still open, and the Linux beta's setup estimate can read folders you never listed.

Free vs Self-Hosted vs Paid

fully free

Free: The whole app on Mac, Windows (beta) and Linux (beta). No account, no telemetry, no paid tier; the author takes tips through Gumroad. App code is MIT. It reads pictures, PDFs, documents, spreadsheets and presentations (xlsx, pptx, ods, odp), audio and video, plus code if you turn code search on. The model it downloads, ggml-org's Q8_0 GGUF build of EmbeddingGemma 2, is Apache 2.0.

Self-hosted: Runs locally. Mac is v0.6.2 (October 21, 2026) via DMG or brew install --cask arahim3/tap/digup and needs Apple Silicon and macOS 14+. Windows and Linux are v0.7.0-beta.2 (October 18, 2026): an unsigned per-user Windows installer for 64-bit Windows 10 or 11 (SmartScreen will warn), and a Linux .deb (dig-up) or AppImage. The model is an 865 MB one-time download from Hugging Face, checked by size and SHA-256. It goes online only for that download and a daily update check you can turn off. Three security advisories so far, all fixed: a high-severity one where code search ran git with an indexed repo's own config (fixed in Mac 0.6.2 and beta.2) and two crash/memory bugs in the Windows and Linux file readers (fixed in beta.2). Open reports include a Windows crash on non-ASCII file names that the maintainer can't yet reproduce.

Paid: No paid tier and no cloud service. The cost is disk space for the model and index, and CPU, GPU and battery during the first indexing pass.

Free on every platform with no account and no cloud, and the model weights are Apache 2.0 too. The only cost is the machine time for the first indexing pass.

What to do by team size

Solo
free; one DMG or installer and an 865 MB model download
Small team
free, installed per machine
Medium team
free, but indexes are per user and there's no shared search
Large team
free, though there's no central management; deploy it as a personal tool only
Self-hosting ops:trivial

Get tools like this every Wednesday

One featured tool, three on the radar. No fluff.

Score
78/100 · B+
Adoption21/30
Maintenance25/25
Community7/20
License15/15
Analysis10/10

A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores

Trust Signals

Author also built: ARahim3/kaggle-tpu-lab (608 stars)

About

Owner
Abdur Rahim (User)
Stars
5,588
Forks
411

Also by Abdur Rahim

Explore Further

More tools in the directory