ExplosiveCoderflome/AI-Novel-Writing-Assistant

面向长篇小说创作的 AI Native 开源系统，用 Agent、世界观、写法引擎、RAG 和整本生产工作流，帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel creation — from idea to full chapters, with structured planning, worldbuilding, and agent-driven workflows.

What it solves

This project provides a comprehensive workstation for long-form and short-form AI-assisted novel writing. It solves the difficulty of maintaining consistency in world-building, character arcs, and plot progression over thousands of words, transforming a simple idea into a structured, complete book.

How it works

The system uses an "AI Director" (available in V1 and V2 versions) to manage the creative process. It guides the user from initial inspiration to world-building, character creation, and chapter-by-chapter planning. The production chain involves assembling a context (including world rules, character states, and style guides), generating a draft, reviewing it against specific rules, and performing local revisions before saving. It also features a "Book Analysis" tool to decompose existing works for structural and stylistic reference.

Who it’s for

  • Aspiring authors who are new to novel writing and need guidance on structure and planning.
  • Experienced writers who need tools to maintain long-term lore and character data.
  • Developers interested in AI-driven long-form content production workflows.

Highlights

  • AI Director Modes: Supports fully automated progression or semi-automated stage-by-stage confirmation.
  • Consistency Tools: Dedicated libraries for world-building, character relationships, and plot foreshadowing.
  • Style Engine: Custom expression rules and "Anti-AI" rules to control the prose style and reduce generic AI patterns.
  • RAG Integration: Uses Qdrant for knowledge base retrieval to bring long-term reference materials into the writing context.
  • Token Optimization: Implements input caching strategies to reduce costs by reusing stable world rules and style guides across chapters.
  • Multi-format Output: Ability to extend novels into comic storyboards or short drama scripts.

Related

  • Project
    EthanYoQ/AI-Novel-Writer

    AI Novel Writer is a desktop app that orchestrates AI‑assisted long‑form fiction writing. It lets you configure any OpenAI‑compatible or Gemini model, manages a structured workflow (premise → characters → outline → chapter blueprint → draft → review → revision → final), stores all project data locally, and offers features like chapter‑level generation, failure recovery, automated review, batch tasks, and a frozen DeepSeek Harness web plug‑in.

  • Project
    NEKOparapa/ReaDreamAI

    An AI-powered platform that automates the creation of novels, including text generation, consistent character illustrations, and video adaptations.

  • Project
    sorker/ai-shotlive

    AI ShotLive Director is an open‑source, React + Express (or Electron) platform that turns novels or story outlines into short videos or motion comics. It uses a keyframe‑driven workflow (first/last frames → interpolation) and lets you plug in any text, image, video or audio model (OpenAI, Anthropic, Google, AntSK, etc.). Features include novel‑to‑script conversion, asset generation (character look‑books, scene concepts), a grid storyboard editor, multi‑track video editing with AI subtitles/TTS, and full backup/restore. Deployable via Docker, local SQLite, or as a desktop app, and licensed under CC BY‑NC‑SA 4.0.

  • Project
    notnotype/neuro-book

    NeuroBook is an engineering-focused writing environment that integrates AI agents with structured world-building and plot-tracking tools to help authors write consistent, high-quality long-form fiction.

  • Project
    Deng-m1/MaliangAINovalWriter

    Maliang AI Novel Writer (AINoval) is an open‑source web platform that lets Chinese web‑novel authors write long‑form fiction with AI assistance. It bundles a Flutter‑Web rich‑text editor, hierarchical content management, AI‑driven outline/scene generation, structured world‑building trees, prompt/preset handling, and a full admin console for user, model, cost and content‑moderation management. The backend is Spring Boot 3 (Java 21) using LangChain4j for LLM orchestration, MongoDB for storage and Chroma for vector embeddings. Deploy with a single Docker‑Compose file, then create an admin account via the provided script. Ideal for solo writers, writing teams, or platform operators who need AI‑augmented novel creation and robust operational tooling.