GHOSTNOTE AI：讓不願埋藏的回憶化為故事
👻 GHOSTNOTE AI: Some Memories Refuse to Stay Buried
GHOSTNOTE AI 是一款由 AI 驅動的數碼日記，可將故事構思、神秘事件和個人回憶轉化為富有氛圍的敍事。項目採用 React 和 TypeScript 前端，支援可替換的模型供應商，包括 Ollama 和本機託管的開放權重模型。用戶可儲存及重看故事，並在支援的情況下將已儲存內容保留在本機。
This is my submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine.
What if your computer could turn mysterious notes and forgotten memories into haunting stories?
Meet GHOSTNOTE AI — a spooky, AI-powered digital diary inspired by haunted terminals, forgotten memories, and the supernatural side of technology.
🕯️ What I Built
GHOSTNOTE AI is a digital archive that transforms story ideas, mysterious incidents, and personal reflections into atmospheric narratives.
Inspired by the Ghost in the Machine theme, I wanted to combine AI storytelling with an immersive, cinematic interface that feels like stepping into a haunted digital archive.
✨ Features
👻 AI Storytelling: Transform notes and story ideas into atmospheric narratives.
🌑 Cinematic UI: A dark, mysterious interface inspired by supernatural archives.
📓 Digital Archive: Save and revisit your stories.
🔐 Privacy-Conscious Design: Keep saved entries local wherever supported.
🧠 Open AI Architecture: Explore integration with Ollama and open-weight models for greater control over AI inference.
🚀 Live Demo
👉 https://ghostnote-ai-sigma.vercel.app/
💻 Source Code
⭐ https://github.com/SOUMYADEEPDEY1217/GHOSTNOTE
Contributions, feedback, and ideas are welcome!
🛠️ How I Built It
I used AI-assisted development to build the application, focusing on a polished web experience and a practical storytelling workflow.
The project uses a React and TypeScript-based frontend. Its AI architecture is designed to support replaceable model providers, including Ollama for locally hosted open-weight models.
My goal is to make the application adaptable rather than permanently dependent on a single proprietary AI provider.
🌍 Why Does Open Innovation Matter?
Open innovation gives developers the freedom to experiment, adapt, and build beyond the limitations of a single provider.
An open-weight AI approach can offer several advantages:
Privacy: Properly configured local inference can keep private prompts and stories on the user's device.
Offline access: A downloaded model can run without an internet connection when the local environment is configured correctly.
Flexibility: Developers can switch compatible models and customize their behavior.
Independence: Projects can evolve without being completely tied to one proprietary AI service.
For me, open AI is about more than using a model. It's about giving developers and users more control over the technology they build with.
🕸️ The Spirit of It
Halloween celebrates the mysterious, but the idea behind GHOSTNOTE AI goes beyond horror.
Our stories and memories can outlive the devices that hold them. Technology gives us new ways to preserve, reinterpret, and share them.
With GHOSTNOTE AI, I wanted to explore that idea through a digital archive where a forgotten note can become the beginning of something extraordinary.
Some memories refuse to stay buried. Some stories deserve to live on.
🏆 Challenge
Built for the Hacktoberfest Open-Source AI Challenge — Week 4: Ghost in the Machine.
I'd love to hear your thoughts and suggestions!
來源：DEV Community · dev.to