Ghost in the Machine：開源 AI 恐怖故事生成器

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

What I Built

Ghost in the Machine is an AI-powered spooky story generator that brings the supernatural into the world of technology.

Inspired by the idea that machines might remember things humans have forgotten, I built a tool that generates eerie, atmospheric stories using open-source AI.

Users can provide a prompt, choose a setting, and let the AI create a chilling narrative. From abandoned servers and haunted terminals to mysterious messages from forgotten systems, every story explores the strange relationship between technology, memory, and the unknown.

The project interprets the theme Ghost in the Machine quite literally: What if the machine had a story of its own to tell?

Demo

🔗 Live Demo: [Add your deployed link]

🎥 Video Demo: [Add your video link]

Code

💻 GitHub Repository: [Add your GitHub repository link]

How I Built It

The project is built around open-source AI, using an open-weight language model to generate stories.

The core components include:

Open-weight LLM:
AI Runtime:
Frontend:
Backend:
Inference:

The user enters a prompt, which is passed to the language model along with instructions defining the tone, atmosphere, and narrative style.

The model generates a story based on the prompt, creating a personalized spooky experience.

The focus was to make the AI the heart of the project rather than simply adding an AI API as an afterthought.

Why Does Open Innovation Matter?

Open innovation was central to this project.

Using open-source AI makes it possible to experiment with models, customize prompts, and change the underlying model without rebuilding the entire application.

Unlike a closed API, an open-weight model gives developers greater control over how the AI behaves and where inference happens.

This approach also opens up several possibilities:

Privacy: Local inference can keep user prompts on their own machine.
Flexibility: Models can be swapped, customized, or fine-tuned.
Accessibility: Developers can experiment without depending entirely on paid API services.
Independence: The project is less dependent on a single proprietary AI provider.

The most exciting part is that the project can evolve with the open-source AI ecosystem.

A new model can bring better storytelling, stronger reasoning, or a more immersive experience without requiring a complete redesign.

For me, open innovation means having the freedom to build, experiment, and improve without being locked into a single platform.

The Spirit of It

There is something fascinating about the idea that technology might preserve traces of the past.

An abandoned computer, an old terminal, or a forgotten server can feel like a place where something remains even after everyone has left.

This project explores that feeling through AI-generated stories.

What if the machine remembers?

What if the last message on an abandoned server was never meant for us?

And what if the ghost was never supernatural at all, but something we left behind?

Sometimes, the scariest stories are the ones that make us question what we thought was impossible.

Built for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine.