I Built an Offline AI That Organizes My Downloads So I Don't Have To
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady . We've all been there. You download an assignment, a certificate, a PDF, a screenshot, or an invoice, thinking you'll organize it later. But later rarely comes. Before you know it, your Downloads folder is filled with files named document(3).pdf , final_final_v2.docx , and IMG_20261023.png . Finding…
For the Hacktoberfest Open-Source AI Challenge, the author created a desktop application called HushFile that organizes files automatically without internet access. The program quietly monitors the Downloads folder, understands the contents of each file using locally run AI models, and names them meaningfully before moving them into relevant folders.
HushFile handles multiple file formats such as PDFs, Word documents, spreadsheets, images, audio recordings, and text files. It uses open-weight AI models running locally on the user's computer for tasks like OCR on scanned documents, text understanding, image interpretation, and generating summaries. The program maintains a SQLite-based undo journal to allow users to reverse file moves and check the results.
One of the key features is semantic search using local text embeddings and a vector database, enabling users to find files by their content and metadata rather than just their names. The application also provides Quick-Info cards that explain how files were organized, making the AI's decisions more transparent.
The demo shows how to download a document, let HushFile organize it, search for it using natural language, and undo the move if needed. The project is open-source, built with Python, and runs locally on Windows, Linux, and macOS. The full setup instructions are available on the GitHub repository.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
