AIxiezuo is an AI-powered novel writing system designed for authors and content creators. It automates the generation of novel chapters, manages world-building elements, and remembers context, significantly streamlining the creative process. The system leverages LangChain and supports a wide array of large language models, offering flexibility and power to users looking to accelerate fiction production.

How It Works

The project utilizes the LangChain framework to orchestrate interactions with various large language models (LLMs). It features a robust state management system that saves and recalls chapter-specific details, character progression, and world bible information. This allows for consistent narrative development and context awareness across generated chapters. A web interface provides an intuitive platform for interactive writing, project management, and model configuration.

Quick Start & Requirements

• Installation: Clone the repository and install dependencies using pip install -r requirements.txt.
• Configuration: Set up API keys for desired LLMs (DeepSeek, OpenAI, Anthropic, Google, or third-party) in a .env file.
• Execution: Launch the web interface via python start_web.py and access it at http://127.0.0.1:5001. Command-line usage is available but less convenient.
• Supported Models: DeepSeek, OpenAI (GPT-4, GPT-3.5), Anthropic (Claude), Google (Gemini), and DSF (third-party APIs).

Highlighted Details

• Multi-LLM Support: Integrates with DeepSeek, OpenAI, Anthropic, and Google models, plus custom third-party APIs.
• State Management: Persists chapter-specific protagonist states, inventory, relationships, and plot summaries in JSON files.
• World Bible: Maintains a structured "world bible" JSON file for consistent world-building elements like settings, power systems, locations, and NPCs.
• Project Isolation: Manages multiple novel projects independently.

Maintenance & Community

No specific details on contributors, community channels, or roadmap were provided in the README.

Licensing & Compatibility

Released under the MIT License, permitting commercial use and modification with attribution.

Limitations & Caveats

The README notes that command-line usage is inconvenient compared to the web interface. Specific performance benchmarks or detailed setup time estimates are not provided.