autonovel

autonovel

An autonomous pipeline for writing, revising, typesetting, illustrating, and narrating a complete novel. From a seed concept to a print-ready PDF, ePub, audiobook, and landing page — all generated by AI agents.

Inspired by karpathy/autoresearch: the same modify-evaluate-keep/discard loop, applied to fiction.

First novel produced: The Second Son of the House of Bells — 19 chapters, 79,456 words. See the autonovel/bells branch.

---

Quick Start

# Clone and setup
git clone <repo-url> && cd autonovel
cp .env.example .env    # Add your API keys

# Install dependencies
uv sync

# Generate a seed concept (or write your own in seed.txt)
uv run python seed.py

# Run the full pipeline
uv run python run_pipeline.py --from-scratch

---

The Pipeline

Phase 1: Foundation

Build the world, characters, outline, voice, and canon from a seed concept. Loop until foundation_score > 7.5.

Phase 2: First Draft

Write chapters sequentially. Evaluate each one. Keep if score > 6.0, retry if not. Forward progress over perfection.

Phase 3a: Automated Revision

Adversarial editing → apply cuts → reader panel → generate briefs → rewrite chapters. Plateau detection stops the loop when scores stabilize.

Phase 3b: Opus Review Loop

Send the full manuscript to Claude Opus for dual-persona review (literary critic + professor of fiction). Parse actionable items. Fix the top issues. Repeat until the reviewer runs out of major items.

Phase 4: Export

Rebuild docs, typeset in LaTeX, generate art, produce audiobook scripts, build ePub, create landing page.

See PIPELINE.md for the full technical specification.

---

Tools (27 Python scripts)

Foundation

Tool	Purpose
seed.py	Generate seed concepts
gen_world.py	Seed → world bible
gen_characters.py	Seed + world → character registry
gen_outline.py	Outline with beats and foreshadowing
gen_outline_part2.py	Foreshadowing ledger
gen_canon.py	Cross-reference hard facts
voice_fingerprint.py	Voice analysis and discovery

Drafting

Tool	Purpose
draft_chapter.py	Write a single chapter with anti-pattern rules
run_drafts.py	Batch sequential chapter drafter

Evaluation

Tool	Purpose
evaluate.py	Mechanical slop scorer + LLM judge
adversarial_edit.py	"Cut 500 words" analysis → classified cuts
compare_chapters.py	Head-to-head Elo tournament
reader_panel.py	4-persona novel-level evaluation
review.py	Opus dual-persona review with stopping conditions

Revision

Tool	Purpose
gen_brief.py	Auto-generate revision briefs from feedback
gen_revision.py	Rewrite a chapter from a revision brief
apply_cuts.py	Batch adversarial cut applicator

Art & Cover

Tool	Purpose
gen_art.py	Art pipeline: style, curate, ornaments, vectorize
gen_art_directions.py	Generate diverse art directions for curation
gen_cover_composite.py	Text overlay on cover art
gen_cover_print.py	Print-ready full-wrap cover (Lulu/KDP specs)

Audiobook

Tool	Purpose
gen_audiobook_script.py	Parse chapters into speaker-attributed scripts
gen_audiobook.py	Generate multi-voice audio via ElevenLabs

Orchestration

Tool	Purpose
run_pipeline.py	Full pipeline orchestrator (seed → finished novel)
build_arc_summary.py	Regenerate arc summary from chapters
build_outline.py	Regenerate outline from chapters

---

File Structure

…

---

How It Works

The novel is five co-evolving layers:

  Layer 5:  voice.md          — HOW we write
  Layer 4:  world.md          — WHAT exists
  Layer 3:  characters.md     — WHO acts
  Layer 2:  outline.md        — WHAT HAPPENS
  Layer 1:  chapters/ch_NN.md — THE ACTUAL PROSE
  Cross-cutting: canon.md     — WHAT IS TRUE

Changes propagate both down (lore change → outline change → chapter revision) and up (writing reveals a gap → update lore → check downstream). The pipeline tracks propagation debts in state.json.

Two Immune Systems

1. Mechanical (evaluate.py, no LLM): regex scans for banned words, fiction clichés, show-don't-tell violations, sentence uniformity.

2. LLM Judge (evaluate.py, separate model): scores prose quality, voice adherence, character distinctiveness, beat coverage.

The Opus Review Loop

After automated revision cycles, the full manuscript goes to Claude Opus with this prompt:

"Read the below novel. Review it first as a literary critic and then as a professor of fiction. Give specific, actionable suggestions for any defects you find. Be fair but honest. You don't have to find defects."

The dual-persona review catches what automated tools can't: prose-level repetition, character thinness, ethical gaps, structural monotony. The loop continues until the reviewer's items are mostly qualified hedges rather than real problems.

---

API Keys

The pipeline uses three external services:

Service	Key	Used for
Anthropic	ANTHROPIC_API_KEY	Writing, evaluation, review (Sonnet + Opus)
fal.ai	FAL_KEY	Cover art and ornament generation (Nano Banana 2)
ElevenLabs	ELEVENLABS_API_KEY	Multi-voice audiobook generation

Copy .env.example to .env and fill in your keys. Only the Anthropic key is required for the core pipeline. Art and audiobook are optional.

---

Production History

The first novel, The Second Son of the House of Bells, was produced through this pipeline:

• Foundation: World bible, 8 characters, 24-chapter outline, voice discovery
• Drafting: 24 chapters, 75,698 words, sequential with evaluation
• Revision: 6 automated cycles + 6 Opus review rounds
• Structural: 24 → 19 chapters through 4 merges
• Art: Linocut cover (Nano Banana 2), 19 woodcut chapter ornaments (vectorized)
• Audiobook: 19 chapters parsed into 4,179 speaker-attributed segments
• Final: 79,456 words, 6 review rounds, all major items resolved

---

Inspiration

• karpathy/autoresearch — the autonomous research loop
• Brandon Sanderson's writing lectures (Laws of Magic, character sliders)
• K.M. Weiland's Creating Character Arcs
• Blake Snyder's Save the Cat
• Ursula K. Le Guin's "From Elfland to Poughkeepsie"
• slop-forensics and EQ-Bench Slop Score