OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Novel Studio

Novel Studio is a self-hosted, open-source Go AI writing engine that coordinates multiple agents to plan and generate long-form fiction. It combines story-world and character reasoning, arc-based chapter planning, RAG-backed continuity memory, chapter-by-chapter drafting and review, and resumable progress.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Novel Studio — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Novel Studio when a fiction project benefits from explicit planning and continuity records across many chapters, or when interrupted generation needs to resume from saved state. It is suited to a staged production process rather than free-form continuation in a chat window.

Who it is for

  • Writers developing long-form fiction or serialized novels who need structured continuity across chapters.
  • Story studios seeking a staged workflow for planning, drafting, review and recovery.
  • Developers interested in adapting an open-source, self-hosted multi-agent writing pipeline.

Documented uses

  • Develop a story world, characters and book-wide chapter navigation before drafting.
  • Plan the next short chapter window around character decisions, point-of-view limits and cause-and-effect.
  • Carry sourced story facts and writing methods into chapter generation using RAG.
  • Draft and review chapters one at a time, admitting only accepted prose and actual outcomes into story canon.
  • Resume interrupted planning and writing from saved checkpoints, and inspect production progress in a dashboard.
Before you choose

Requirements & limits

The project is open source under Apache-2.0. It supports macOS and Linux, with Windows use through WSL2. Release installation does not require Go; source execution requires Go 1.25.5 or a compatible newer version. The dashboard requires Python 3.9 or later.

  • A usable text-model provider is required; the supplied project documentation does not specify supported providers.
  • Embedding and Qdrant are optional RAG enhancements, not stated prerequisites for every workflow.
  • Whether a run is fully offline depends on the chosen model and supporting services, as well as whether online tools are invoked.
  • A pipeline call handles at most the next chapter’s rendering and review; longer projects advance through repeated runs.
  • Initialization can stop before planning or drafting, and delivery of a short story’s full-text final review is a separate explicit stage.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and check a Novel Studio setup

Install a release or run the current source checkout, then diagnose configuration and make a minimal model request.

Before you start

  • macOS or Linux; Windows users need WSL2.
  • A configured text-model provider for the minimal model request.
  • For source runs, Go 1.25.5 or a compatible newer version.

Steps

  1. For a release installation, run the command below.

    Documented command
    curl -fsSL https://raw.githubusercontent.com/Xiaoyangy/novel-studio/main/scripts/install.sh | sh

  2. For source mode, clone the repository, enter its directory and run ./scripts/run-local.sh doctor.

  3. Run novel-studio doctor to check the system, directories, configuration, dashboard and optional RAG dependencies.

  4. Run novel-studio --check to make a minimal real model request and check the provider, model and fallback route.

Expected outcome

The release or current checkout is installed or available to run, and the documented checks report configuration status; `--check` exercises a minimal model request.

Guide limitations

  • The doctor command does not call a model or advance story state; --check does call a model.
  • The release installer and source workflow are distinct. Source runs require Go; release installation does not.
  • The README says the dashboard requires Python 3.9 or later.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Novel StudioDevelop a story world, characters and book-wide chapter navigation before drafting.Self-hostedThe project is open source under Apache-2.0. It supports macOS and Linux, with Windows use through WSL2. Release installation does not require Go; source execution requires Go 1.25.5 or a compatible newer version. The dashboard requires Python 3.9 or later.
Insurance Agentic AIRoute insurance questions to a life, home or auto specialist.Docker, Self-hosted, Web
AI ChatkitCreate and orchestrate agents with custom behavior logic.Linux, Self-hosted, Server, WebThe repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Xiaoyangy/novel-studio · Official homepage title · retained in its source language
How we review sourcesSuggest a correction