# mshumer/gpt-author

Repository: https://github.com/mshumer/gpt-author
Canonical: https://ross.abutalabs.com/products/gpt-author
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-04-03T03:14:59+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 83
- inputs: {"age_days": 1170, "days_push": 882, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2530, forks 349 (observed 2026-08-28T04:06:58.804969+00:00)

## What it is
A Jupyter notebook-based tool that chains GPT-4/Claude 3 and Stable Diffusion API calls to generate complete fantasy novels from a user prompt, including cover art, and compiles them into EPUB files. It was created by Matt Shumer and gained popularity as a demonstration of long-form AI creative writing.

## Use cases
- generate a fantasy novel from a prompt
- write an entire book with AI and export as epub
- create chapter outlines and storylines with GPT-4
- generate ebook cover art with stable diffusion
- experiment with chained LLM calls for long-form writing
- produce a multi-chapter novel in minutes

## When to choose
- you want a quick, end-to-end demo of AI novel generation producing an EPUB
- you want a hackable notebook to experiment with multi-step LLM creative pipelines
- you want to try the Claude 3 version for higher-quality prose

## When to avoid
- you need production-grade, controllable, or editable book-writing software
- you want fine-grained editorial control over plot and characters
- you cannot or will not pay for OpenAI/Anthropic API usage

## Facets
- artifact type: application
- maturity: experimental
- function: llm-inference, prompt-engineering, stable-diffusion, pdf
- domain: artificial-intelligence, large-language-models
- platform: python
- tags: novel-generation, epub, gpt-4, claude-3, jupyter-notebook, creative-writing, ai-generated-books, natural-language-processing, web-server

## Member repositories
- mshumer/gpt-author (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.804969+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:21.421325+00:00, confidence not recorded.
  - readme: https://github.com/mshumer/gpt-author (fetched 2026-08-28T04:06:58.804969+00:00, sha 8f1b2d0f7d9b)
- Data as of 2026-08-30T08:39:29.467469+00:00.