Discover and explore top open-source AI tools and projects—updated daily.
datacrystalsLLM story writer for full-length novels
Top 98.8% on SourcePulse
AIStoryWriter is an LLM-powered tool designed to generate high-quality, long-form stories, including novellas and novels, from user-provided prompts. It targets users seeking to create substantial narratives with ease, offering benefits such as straightforward setup, customizable prompts and model choices, and support for both local and cloud-based language models.
How It Works
The project leverages large language models to construct coherent narratives of significant length. Its core approach involves processing user prompts to generate story outlines and then chapter-by-chapter content. A key design choice is its flexibility, allowing users to select and configure various language models, including local models managed via Ollama or cloud-based services like Google and OpenRouter. The system also features automatic downloading of required models for Ollama, simplifying the setup process.
Quick Start & Requirements
To get started, clone the repository, install Ollama for local model support, and run the main script: sh ./Write.py -Prompt Prompts/YourChosenPrompt.txt. The system automatically downloads necessary models. Users can customize prompts in Writer/Prompts.py or Writer/Config.py, and model selection can be overridden via command-line arguments. For providers requiring API keys, copy .env.example to .env and add credentials. Hardware recommendations for different GPU capabilities are available on a dedicated page.
Highlighted Details
Maintenance & Community
The project encourages community involvement through bug reporting and feature requests via GitHub Issues, discussions in GitHub Discussions, and code contributions via Pull Requests. For real-time interaction and support, users can join the project's Discord server.
Licensing & Compatibility
This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0). This license requires that any modified source code used to provide a service over a network must be made available to the users of that service.
Limitations & Caveats
Current areas for improvement include reducing repetitive phrases in generated prose, enhancing chapter flow and narrative cohesion, addressing story pacing issues, and optimizing overall generation speed without compromising output quality.
7 months ago
1 day