DigUp lets users find Mac files by describing them, not remembering their names

There’s a particular kind of frustration that comes with knowing a file exists somewhere on a computer but having absolutely no idea what it’s called. Was that screenshot saved as IMG_4837? Which PDF contained that clause? And where did that podcast recording mention the thing worth remembering? DigUp wants to end the filename guessing game, letting Mac users search for files by describing what they remember instead. The free, open-source app uses Google’s EmbeddingGemma 2 to search across photos, documents, PDFs, audio recordings and videos, all without sending personal files to the cloud.

DigUp turns everyday descriptions into file searches

Available for Apple Silicon Macs running macOS 14 or later, DigUp lets users select folders to index and then search them using natural language. A query such as “a dog near water” can find a relevant photo, while “where they talk about sleep” can jump to the appropriate moment in a podcast. Searching for a clause in a lease can open the relevant PDF page, while a query such as “payment declined error” can locate a screenshot containing those words.

What’s more, is that it can even search code when the optional code-search feature is enabled, finding functions based on what they do rather than what they’re called. The secret sauce is EmbeddingGemma 2, Google’s 740-million-parameter multimodal embedding model. Instead of treating text, images, audio and video as completely separate search problems, it maps them into a shared space where content with similar meanings can be matched.

DigUp also combines semantic search with exact-word matching, which matters when looking for something specific like an invoice number or error code. The app downloads its roughly 865MB model once and runs searches locally. The developer says indexed files remain on the Mac, with no account or telemetry required. The catch? Initial indexing can take a while, especially when dealing with a large media library.

DigUp isn’t alone, but its approach has a few tricks

Tools such as Apple’s Spotlight and other semantic-search or local knowledge-retrieval apps already help users find information without relying entirely on filenames. However, DigUp’s difference is its focus on searching across multiple media types in one place, including jumping to specific moments in recordings, matching video frames, opening relevant PDF pages, and searching code. Its combination of semantic matching and exact-word search also helps balance fuzzy descriptions with precise queries. Unlike cloud-based AI search services, DigUp keeps the work on the Mac, although it currently requires Apple Silicon and users must choose which folders to index.

RELATED COVERAGE: