GHOSTBYTE 👻 — A Little Memory. An Endless Afterlife.

Description and use

GHOSTBYTE is a local‑first web app that stores personal memories in SQL Server, lets users query them with a local AI model, and generates ghost stories, all offline and without sending data to external APIs.

Problem

Personal memories are private and often fade; users need a way to preserve and revisit them without relying on third‑party AI services.

Outcome

GHOSTBYTE enables users to persist personal memories, query them with local AI, and generate ghost stories, all while keeping data on the user’s machine and functioning offline.

Workflow

• Install Node.js, Microsoft SQL Server, and Ollama.
• Download the model with ollama pull qwen2.5:1.5b.
• Configure the database connection in the .env file.
• Start the application with npm start.
• Open http://127.0.0.1:3000 to use the UI.
• Create, query, and generate stories locally using the web interface.

Evidence

GHOSTBYTE is a local-first, AI-powered memory archive that gives forgotten memories a second life.

Source

Run GHOSTBYTE locally: Install Node.js, Microsoft SQL Server, and Ollama. Download the model using ollama pull qwen2.5:1.5b. Configure the database connection in your .env file. Start the application with npm start. Open http://127.0.0.1:3000.

Source

The application runs locally, and the AI uses your local Ollama installation.

Source