Uncategorised decision

AI Website Directory

A small, single-tenant directory with an API is realistic for one capable developer to build and maintain; most of the product's durable value (community, traffic, curation) would be lost and is not reproduced by a simple replacement.

Visit website

Built by Kites.Dev, who ships 6 products in this index

You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off40 h to build

$35/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

  • Users submit tool listings, community votes and reviews, listings rank and appear in leaderboards, and an API exposes published tools and categories.

What it still won’t have

  • Existing community, traffic, and vendor relationships
  • Established leaderboard and historical votes
  • Any proprietary curation or editorial processes
  • Built-in MCP integration examples and existing developer API keys

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

AI Website Directory 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

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

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

Not run yet
Build a minimal AI tools directory using Next.js (React) for the frontend, Express (Node.js) for the API, and PostgreSQL for storage. Core features in scope: public browseable category and search pages, tool detail pages with screenshots, a submit form for new tools (including image upload to S3-compatible storage), community voting (one vote per IP/user), an admin review UI to approve/reject submissions, an authenticated developer API endpoint requiring x-api-key that returns JSON /api/products and /api/categories, and a scheduled job to recalculate leaderboards. Out of scope: multi-tenant accounts, paid listings, advanced analytics dashboards, and a full gamified reputation system. Include API-key issuance and revocation endpoints, input validation, rate limiting, logging, error handling, unit and integration tests, and deployment configs for Vercel (frontend) and a single DigitalOcean droplet or managed Postgres. Provide a README with setup, seeding, and migration commands.
How we checked2 sources · 2/3 runs agreed · evidence score 79

How the score was reached

  • Build verdict base78
  • 2 cited sources+1
  • Evidence score79

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 · 2

Every page the run actually retrieved.

Integrity checks

What held up, and what did not.

! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded