StoryCraftr
Command-line tool that helps you outline, worldbuild and draft book chapters with an LLM you choose.
Outline, worldbuild and draft chapters from the terminal with OpenAI, OpenRouter or Ollama.
StoryCraftr is an open-source command-line assistant for writing books with AI. It suits writers comfortable in a terminal who want outlines, worldbuilding notes and chapters organized as project files.
What it is
You start a book project with storycraftr init, set a language, genre, author and model provider, then run commands for outlines, worldbuilding and chapters. A chat mode lets you iterate, for example insert a new chapter mid-book. It runs on LangChain and supports OpenAI, OpenRouter and Ollama.
Who it's for
It suits novelists who like scriptable workflows and project folders with a storycraftr.json config. It does not suit writers who want a point-and-click editor; the only interface besides the terminal is a VS Code extension.
Key features
Book project init
storycraftr init sets title, languages, genre, author and model in a project.
Outline generation
Commands create a general outline, character summaries and chapter synopses.
Worldbuilding commands
Generate geography, history, technology or a magic system for your setting.
Chapter drafting
Write chapters, cover text and epilogues from your synopsis.
Chat with iterate
Interactive chat can insert or rewrite chapters, outlines and worldbuilding.
Multiple model providers
Works with OpenAI, OpenRouter and Ollama via LangChain.
Up and running in 3 steps
Our honest verdict
What's great
- Multi-language projects are built in: init takes a primary language and alternate languages.
- You can pick OpenAI, OpenRouter or a local Ollama model per project in storycraftr.json.
- Worldbuilding, outline and chapter commands share one project, so context stays together.
- A VS Code extension lets you start the chat from inside your editor.
Where it falls short
- It is a command-line tool installed with pipx or uvx from a pinned git tag; there is no standalone installer or graphical editor.
- You supply your own API key or run a local Ollama model, which means paying per use or having suitable hardware.
- The latest release is v0.12.0-beta10, so the README itself marks it as beta software.
- The default embedding model is BAAI/bge-large-en-v1.5; the README suggests a lighter one on constrained hardware.
Pricing & license
Free under the MIT licence and no paid plan is shown in the README. You pay your model provider, or run Ollama yourself.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Which AI providers does it support?
The README says OpenAI, OpenRouter and Ollama work out of the box, selected with llm_provider in storycraftr.json.
Can I use it without paying for an API?
The README lists Ollama for self-hosted models, which usually needs no key, but you must run Ollama on your own hardware.
Is there a graphical interface?
No. It is a command-line tool, though a VS Code extension can launch the chat for you.
