N-CODE GhostLog AI: Turning Forgotten Logs into Halloween Stories with Gemma

Description and use

N‑CODE GhostLog AI uses a local Gemma 3 1B model via Ollama to generate Halloween stories from user‑supplied logs, validating JSON structure and story length.

Problem

Generate creative Halloween stories from fictional terminal logs without executing commands or diagnosing security incidents.

Outcome

The application passes 19 automated tests, generates stories with 149–155 words, and returns three clues, all validated against a JSON schema.

Workflow

• 1. User enters fictional terminal logs and selects a mood (unsettling, melancholic, playful).
• 2. Browser sends data to /api/haunt endpoint.
• 3. Server validates input and forwards request to Ollama’s /api/generate with a structured‑output prompt.
• 4. Gemma returns JSON containing title, story, clues, and final line.
• 5. Server validates JSON against a schema, checks story length (110–190 words), and retries once if needed.
• 6. Browser renders the story, clues, and final line; user can download the result as Markdown.

Evidence

I built N-CODE GhostLog AI, a local Halloween storytelling application powered by Gemma 3 1B through Ollama.

Source

Users enter fictional terminal logs, choose an unsettling, melancholic, or playful mood, and decode a transmission. Gemma generates a title, a 110–190 word story, three clues, and a haunting final line.

Source

Verified results on October 28, 2026: 19 automated tests passed; actual API generation produced 149 story words and browser generation produced 155 words.

Source

The application uses Python's standard library for the local HTTP server and HTML, CSS, and JavaScript for the interface. It needs no pip or npm packages to run.

Source