Echoes After Midnight: An AI Ghost That Lives Inside Your Computer

What if the computer you are investigating is also the thing hiding the truth?

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

What I Built

Echoes After Midnight is a concept for a local-first, AI-powered paranormal investigation game.

Imagine discovering an abandoned computer containing corrupted logs, forgotten notes, mysterious timestamps, and messages that should not exist. Something happened here. The machine remembers fragments of it, but those fragments do not tell the whole story.

Your mission is to investigate.

Unlike a traditional choose-your-own-adventure game, Echoes After Midnight is designed to let players question an AI character, inspect evidence, connect clues, and develop their own theories about a mysterious incident.

The AI takes on the role of the machine's digital presence. It will help players investigate the evidence, respond to questions, and gradually uncover the story behind the haunting.

The central idea is simple: what if the ghost wasn't in a haunted house, but inside a computer?

I interpreted the Ghost in the Machine theme as both a Halloween mystery and an exploration of how technology can preserve traces of the past.

Demo

🚧 Coming soon!

I'm working on the initial version of Echoes After Midnight. A live demo and project walkthrough will be shared as development progresses.

Code

💻 GitHub repository coming soon!

The source code, setup instructions, and implementation details will be published on GitHub once the initial version is ready.

How I Built It

The project is planned around a React and Vite frontend, a Python backend using FastAPI, and a local AI runtime using Ollama with a compatible open-weight language model.

The interface will use a retro terminal aesthetic, with phosphor-green text, dark backgrounds, subtle glitch effects, and atmospheric animations to create the feeling of exploring a forgotten machine.

The backend is intended to manage the investigation, evidence archive, and interactions with the local AI model.

Rather than relying on a hosted AI API, the goal is to run inference locally so that the core investigation can work without sending conversations to a remote AI provider.

The initial version will focus on one mystery, with a collection of fictional evidence files, clues, and multiple possible endings.

These are the planned technologies and features; implementation details will be updated to reflect the working project.

Why Does Open Innovation Matter?

For this project, open innovation is about more than choosing a different AI model. It is about giving developers and users greater control over how AI works and where their data goes.

1. Local-first AI

Running a compatible open-weight model locally can allow the investigation to continue without sending prompts to a remote AI service. After the model and dependencies are downloaded, the experience can potentially work offline.

2. Privacy and control

Investigation notes, conversations, and locally stored evidence can remain on the user's computer when the application is designed to keep processing and storage local.

3. Freedom to experiment

An open-weight model makes it possible to experiment with different model sizes, prompts, response styles, and behaviors without rebuilding the entire application around a proprietary API.

4. A project others can extend

Publishing the source code will allow other developers to explore the architecture, contribute new mysteries, improve the evidence system, and experiment with different compatible models.

A closed AI API could also generate compelling ghost stories. The difference is that this project aims to put local inference and user control at the center of the experience.

Local AI still uses hardware, memory, and electricity, but it can avoid per-request API charges and reduce dependence on a remote provider.

That trade-off is worth exploring.

The Spirit of It

Computers are full of remnants of the past: old messages, abandoned projects, forgotten photographs, and logs from programs that no longer exist.

Usually, we treat those remnants as files waiting to be deleted.

Echoes After Midnight asks a different question:

What if we could have one last conversation with the machine that remembers them?

The ghost in this story is fictional. But the underlying idea is real: open technology gives us more freedom to preserve, investigate, and reinterpret digital history without handing every piece of it to an external service.

Sometimes the most unsettling thing a computer can say is not something supernatural.

It is something you thought you had forgotten.

---

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