An AI-powered intelligent novel creation assistant, MuMuAINovel streamlines the creative writing process for aspiring and established authors. It leverages multiple large language models to assist users in generating story outlines, characters, world-building elements, and chapter content through an intuitive, guided interface. The project aims to accelerate story development and enhance narrative coherence for individual writers and small teams.

How It Works

MuMuAINovel employs a FastAPI backend and a React/TypeScript frontend. It integrates with major AI providers like OpenAI, Google Gemini, and Anthropic Claude, allowing users to choose their preferred models. Core functionalities include a wizard-driven project setup, AI-assisted generation of story components (outlines, characters, world-building), and robust chapter editing tools. Data is persisted locally using SQLite, supporting multi-user isolation, and the application features a modern, responsive UI built with Ant Design.

Quick Start & Requirements

• Primary Install: Docker Compose (docker-compose up -d).
• Prerequisites: Docker, Docker Compose, Python 3.11+, Node.js 18+, and at least one AI service API Key (OpenAI, Gemini, or Anthropic).
• Setup: Docker deployment is designed for quick setup. Local development requires separate backend and frontend setup.
• Links:
  • GitHub Repo: https://github.com/xiamuceer-j/MuMuAINovel
  • API Docs: http://localhost:8000/docs (Swagger UI), http://localhost:8000/redoc (ReDoc)

Highlighted Details

• Supports multiple AI providers (OpenAI, Gemini, Anthropic) and OpenAI-compatible proxy services.
• Features a guided wizard for AI-driven generation of story outlines, characters, and world-building.
• Includes dedicated modules for character management, relationship mapping, and chapter editing/refinement.
• Offers both local account login and LinuxDO OAuth for authentication.

Maintenance & Community

The project encourages community contributions via Issues and Pull Requests. Specific maintainer details or active community channels (like Discord/Slack) are not detailed in the README.

Licensing & Compatibility

The project is licensed under the GNU General Public License v3.0 (GPL v3.0). This license permits free use, modification, and distribution, including for commercial purposes, but mandates that any derivative works must also be released under the GPL v3.0 license, requiring open-sourcing modifications.

Limitations & Caveats

The project is actively under development, with several features listed as "TODO," including inspiration modes, data import/export, advanced prompt tuning interfaces, and sophisticated plot/setting consistency detection. These indicate areas where current functionality may be limited. The GPL v3.0 license imposes significant restrictions on integrating this software into closed-source commercial products.