This project provides an AI-powered tool for generating multi-chapter novels, focusing on maintaining narrative coherence, character development, and plot consistency. It's designed for writers and hobbyists looking to leverage large language models for long-form creative writing.

How It Works

The system employs a multi-stage generation process, utilizing a semantic search engine (vector-based) for long-range context maintenance. It integrates a knowledge base for local document references and an automatic review mechanism to detect plot contradictions. The core architecture includes modules for world-building, character setting, plot blueprints, intelligent chapter generation, state tracking, and a semantic search engine for context consistency.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt
• Run the application: python main.py
• Prerequisites: Python 3.9+ (3.10-3.12 recommended), pip, and a valid API key for cloud (OpenAI, DeepSeek) or local (Ollama) LLM services. C++ build tools may be needed for some package installations.
• Configuration: Requires setting up API keys, model names, and story parameters in config.json.
• Documentation: Usage Tutorial

Highlighted Details

• GUI-based workflow for setting, directory generation, chapter drafting, and finalization.
• Features a state tracking system for character development and plot points.
• Supports local document integration for knowledge base.
• Includes an automatic review mechanism for consistency checks.
• Offers flexibility in choosing LLM and embedding models (OpenAI, Ollama).

Maintenance & Community

The project is currently in a low-maintenance state due to the developer's academic schedule, with future updates planned for longer breaks. Users are encouraged to report issues and suggest features via the project's GitHub Issues.

Licensing & Compatibility

The repository does not explicitly state a license in the README. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is currently under limited maintenance. Users may need to manually install certain dependencies if pip install -r requirements.txt fails. API response errors (e.g., Expecting value: line 1 column 1 (char 0)) or timeouts may indicate issues with the LLM service provider.