DigUp
Finds images and PDF documents on your computer based on descriptions of their contents. It is a free, open-source tool that processes all files locally for maximum privacy.
The Blend
A developer named ARahim3 has released DigUp, a free desktop application designed to change how people search for files on their personal computers. Instead of relying strictly on file names or basic keyword queries, the software allows users to locate photos, documents, audio recordings, and videos by describing what is inside them in natural language.
According to the project's repository on GitHub, the tool runs Google DeepMind's EmbeddingGemma 2 model locally on the user's computer across Mac, Windows, and Linux platforms. Because all file processing and indexing happen on the device itself, private documents and personal media are never uploaded to remote cloud servers.
In addition to understanding natural descriptions across more than 100 languages, DigUp can pinpoint specific timestamps in media files and recognize text contained within screenshots. However, running an artificial intelligence model locally may draw noticeable memory and power resources, especially on older hardware. It remains an open question whether everyday users will adopt third-party local indexing tools or simply wait for built-in operating system search features to add similar functionality.
Written independently by AI News Smoothie from the reporting listed below. Facts belong to the original publishers. Follow the links for their full coverage.
Ingredients
- 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. · GitHub
DigUp is a free open-source desktop tool that lets users search their local files by content description using an on-device AI model.