JevMade Sign in
← Back to experiments

Apps & data pipelines

jev-linkmap

Suggests internal links by judging candidate target pages and choosing honest anchor phrases already present in the copy.

Bookmark: jev-linkmap Keep this in your collection.
Leave a noteWhat would you try with this? : jev-linkmap

Only you can see your notes.

Source screenshot of jev-linkmap
SOURCE SCREENSHOTFull screenshot ↗

What it does

In the maker's run, it placed 679 links across 334 pages without writing new anchor text.

How you can use it

A developer can use this program to connect related pages on your website. They give the tool a list of your website addresses. The program reads your pages and sends the text to Jev, an outside AI service. Jev then decides which pages should link to each other.

OpenRouter or TypeSafe generates an access key to connect the software to the AI. Your developer provides this key. The tool never writes new text. It only finds matching phrases you already wrote to use as links. Your developer then adds these chosen links to your live website.

Maker-reported (not independently measured by JevMade): 566 pages and 8,460 link decisions (15 candidate targets per page) in one run (author-reported) · 5.95 s wall clock at 32 requests at a time, about half a second and $0.00048 per page (author-reported) · $0.27 for the whole site against about $67 for Claude Opus 5, about 240 times cheaper per page (author-reported) · 679 links placed across 334 pages; 232 pages left unchanged (author-reported)

Primitives
choice, noul
Platform
Python
Added
Project created
GitHub stars
19 (snapshot, not live)

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.