👻 GhostFile: The Ghost of Forgotten Files — Bringing Local AI to Your Digital Memories

👻 GhostFile: The Ghost of Forgotten Files

Every forgotten file has a story. What if AI could help you find it again?

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

What I Built

GhostFile is a local-first AI-powered file investigator that helps users rediscover forgotten files hiding in their computers.

Over time, our devices collect hundreds or even thousands of files. Old documents, duplicate images, forgotten downloads, and files we no longer remember saving can easily get lost.

I interpreted the Ghost in the Machine theme as giving a voice to these forgotten digital memories.

GhostFile scans a user-selected folder and helps identify:

• Forgotten files: Find files that haven't been modified for a long time.
• Duplicate files: Identify exact duplicates using SHA-256 hashing.
• File insights: Explore file types, sizes, and modification dates.
• AI investigation: Ask a local AI assistant to explain file metadata and suggest which files may deserve attention.

GhostFile is designed to help users understand their digital clutter without automatically deleting or moving anything.

Demo

Project screenshots: [

]

Code

GitHub Repository: [https://github.com/padmalochini27-del/GhostFile]

Built with Python and Streamlit.

How I Built It

I built GhostFile using open-source tools and local AI inference.

Technology stack:

• Python – Core application logic
• Streamlit – Interactive dashboard
• Pandas – File data organization and analysis
• SHA-256 – Exact duplicate detection
• Ollama – Local AI inference
• Gemma 3 1B – Local AI model

The application scans selected folders, collects file metadata, identifies older files and duplicate files, and presents the results through a Streamlit dashboard.

For the AI component, I integrated Gemma 3 1B through Ollama, allowing the user to interact with a local AI investigator.

The goal is to keep the investigation local rather than uploading personal file information to an external AI service.

Why Does Open Innovation Matter?

Open innovation made it possible to experiment with AI without depending entirely on closed, paid APIs.

Using Ollama and Gemma 3 1B gave me the opportunity to explore local inference, experiment with an open-weight model, and build an application that prioritizes privacy.

It also made this project more accessible to users who want to experiment with AI on their own computers.

For me, open innovation is not just about using open-source tools. It is about having the freedom to understand, experiment, modify, and build something useful with them.

The Spirit of It

We usually remember the important files we create. But what about the files we downloaded months ago, the documents we saved for later, or the images buried somewhere in a folder?

They quietly remain on our devices, almost like digital ghosts.

GhostFile is my attempt to bring those forgotten files back into view.

Because sometimes, finding an old file can bring back a memory we didn't even know we had forgotten.

Prize Categories

[.Best Use of Gemma]

Built with curiosity, open-source AI, and a little bit of ghost hunting. 👻