Ghost in the Code: Offline Séance with Programming Language Spirits

说明与用途

Ghost in the Code 是一款本地化 AI 游戏，玩家召唤历史编程语言的“幽灵”，解决调试谜题并获得经验值，全部使用 Ollama 上的 qwen2.5:1.5b 模型，完全离线运行。

问题

Provide an offline, local‑first educational game that lets users interact with AI‑powered spirits of historical programming languages without relying on cloud services.

结果

The project delivers a fully offline, local‑first AI game that meets the challenge criteria, demonstrating that educational AI experiences can run on modest hardware without cloud dependencies.

工作流

• Clone the repository from GitHub
• Copy .env.example to .env
• Run npm install ollama and ollama pull qwen2.5:1.5b
• Start the dev server with npm run dev
• Open http://127.0.0.1:5173 in a browser
• Boot the terminal, summon a ghost, and interact
• Solve debugging puzzles and earn XP
• Disconnect Wi‑Fi to verify offline operation

证据

The defining constraint: after you install Ollama and pull the model, core play works without the internet.

来源

Default model: qwen2.5:1.5b (~986 MB, Apache-2.0) — chosen for a GTX 1050 Ti / 16 GB RAM class machine.

来源

No login. No API keys. If Ollama is missing, the setup screen explains the gap instead of silently calling a cloud model.

来源