Games and entertainment decision
Name-gpt
A compact D&D name generator is straightforward for one technical user to implement and run; nothing on the page indicates unreplicable data or infrastructure that would block a DIY replacement.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$50one-off20 h to build
$20/mo3 h/mo upkeep
No published price to break even against.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User submits simple prompts/parameters → server or client generates a name list → display and allow copy/favorite → optional regenerate
What it still won’t have
- Brand, existing user base and traffic
- Polish, analytics, and A/B testing from the vendor
- Any proprietary training data or proprietary backend optimizations the vendor may use
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Name-gpt does not publish a price we could read, so there is nothing to compare against. What building costs is below.
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 minimal D&D name generator as a single-developer project using Next.js (React) for the frontend, a serverless API route (Vercel) or small Node/Express Lambda for name generation, and Postgres (or SQLite) for optional favorites. Core features in scope: parameterized name generation (race, gender, tone), generate/regenerate button, copy-to-clipboard, save favorite names, and a simple admin page to view usage. Out of scope: multi-tenant accounts, payment processing, training custom models, and advanced analytics. Include input validation, error handling for API failures, unit tests for generator logic, and simple integration tests for the API route.
How we checked
How the score was reached
- Build verdict base78
- 3/3 assessment runs agreed+4
- Evidence score82
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 →Integrity checks
What held up, and what did not.
