Writing and content decision
LivingWriter
A capable developer can build a narrow, useful subset (editor + element tracking + AI rewrite/outlines + export) in a week and maintain it; reproducing LivingWriter's full polished multi-platform offering, integrations, and productized AI experience would require more design and engineering investment.
Visit website↗Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need — the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship.
What a replacement has to do
- Author writes chapters in a web editor, stores chapters and elements in a database, invokes AI endpoints to generate outlines/rewrite/summaries or chat about the manuscript, and exports chapters to common formats.
What it still won’t have
- Polished multi-platform native apps and UI/UX refinements
- Proprietary, productized AI tuning and any undisclosed backend optimizations
- Built-in integrations (Canva, Drive) and commercial support/roadmap guarantees
- Any enterprise features or unpublished data/privacy guarantees the vendor advertises
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a single-developer self-hosted minimal LivingWriter clone using Next.js (React) + Tailwind for UI, PostgreSQL for data, Prisma ORM, an S3-compatible bucket for manuscript attachments, and a background worker (Node) for export tasks. Implement: (1) user auth (email/password) and account model; (2) chapter editor with per-chapter version history and autosave; (3) element/board CRUD (characters, settings) linked to chapters; (4) server endpoints that call an external LLM API (provide API-key-based config) for Rewrite, Summarize, Outlines, and Chat; (5) export to DOCX and EPUB; (6) import from DOCX; (7) tests for API endpoints and editor saving, plus basic error handling and retries for AI calls. Out of scope: native iOS/Android apps, multi-seat billing, advanced image-generation UI. Provide Dockerfile, docker-compose for Postgres and the app, and a README with deployment and a small demo dataset.
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 5 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score64
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time — so the same evidence always produces the same number.
How scoring works →Cited sources · 5
Every page the run actually retrieved.
- official productLivingWriter home
- official pricingLivingWriter pricing
- official docsLivingWriter AI features
- open sourceExplosiveCoderflome/AI-Novel-Writing-Assistant
- open sourceRhythmicWave/NovelForge
Integrity checks
What held up, and what did not.
