Haunted Code Reviewer：打造帶有幽靈風格的 AI 程式碼審查工具｜Hacktoberfest 2026
👻 Haunted Code Reviewer: Building an AI Code Reviewer with a Ghostly Twist | Hacktoberfest 2026
Haunted Code Reviewer 是一款 AI 程式碼審查網頁應用程式，可找出程式碼中的潛在錯誤、邏輯問題、未使用變數，並提出改進建議。應用程式以 Python 和 Streamlit 建置，透過 Hugging Face Inference API 連接開放權重模型 Llama 3.1 8B Instruct，並由作者全程使用手機開發及部署。
This is a submission for the "Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine" (https://dev.to/challenges/hacktoberfest-week4-2026-10-26)
What I Built
👻 Haunted Code Reviewer is an AI-powered code review web app that gives developers spooky but useful feedback.
Users paste a code snippet, select a programming language, and summon a ghostly reviewer that identifies potential bugs, logic errors, unused variables, and code improvements.
Inspired by the "Ghost in the Machine" theme, I gave the AI a hidden system prompt that makes it act like a ghost trapped inside a computer while still delivering accurate, beginner-friendly code reviews.
Demo
[Try Haunted Code Reviewer –https://haunted-code-reviewer.streamlit.app/
]
Code
[GitHub Repository–https://github.com/srushtikaware/Haunted-Code-Reviewer ]
How I Built It
I built the app using Python and Streamlit, with the Hugging Face Inference API connecting it to the open-weight Llama 3.1 8B Instruct model.
The app includes:
- A code input area and programming language selector.
- A ghost-themed interface with custom CSS.
- An AI review system prompt that combines technical accuracy with spooky commentary.
- Secure API key management through Streamlit Secrets.
I developed and deployed the project entirely from my phone using GitHub Codespaces, GitHub, and Streamlit Community Cloud.
Why Does Open Innovation Matter?
Open innovation made this project possible without expensive hardware or proprietary AI infrastructure.
Using an open-weight model through Hugging Face allowed me to experiment with AI-powered code review using accessible tools. Open-source frameworks like Streamlit made it easy to build and share the application.
This project showed me how open tools can lower barriers to development and help beginners participate in AI innovation.
The Spirit of It
Building this project entirely from my phone was a challenge of its own. From debugging indentation errors to troubleshooting cloud deployment, every obstacle taught me something new.
The most exciting moment was seeing my own AI-powered app open in a browser after working through those challenges. It reminded me that creativity and persistence matter more than having expensive equipment.
Prize Categories
Open-Source AI Challenge
來源：DEV Community · dev.to