Hosted trial
$0once
25 generated items
One site · One trial per verified customer for this product
Try 25 items freeCrawlune / AI visibility
Check AI crawler access.
Find the content gaps.
Audit your WordPress pages for missing answer blocks, weak structure and crawler restrictions. Manage training and retrieval policies separately, and publish llms.txt from your content. These local features are free without an account. Crawlune measures your site; it does not promise citations.
A useful first session, without an account
Check access. Pick one page to improve.
Start with the parts your site can measure: crawler directives, content structure and missing answer blocks. The local audit, crawler controls and llms.txt require no license.
Your first audit
- 1. Install Crawlune in WordPress
In Plugins → Add New, search for “Crawlune – AI Crawler Controls”, install and activate it. Open WP Shelf → Crawlune → Visibility.
- 2. Review access before changing it
Check which rules affect training and which affect search retrieval. Choose a crawler policy deliberately. Allowing a crawler does not promise a visit or a citation, and robots.txt relies on cooperating crawlers.
- 3. Open Pages and work through one weakness
Start with a low-scoring page and inspect its signal breakdown. Add an opening answer, source or useful heading where the content supports it, then review the page’s audit again.
llms.txt is a proposed convention. Publishing it does not guarantee crawling, ranking or citations.
Optional hosted AI
Try 25 items. Add a pack when you need it.
The WordPress plugin and its local tools stay free. Hosted rewriting requires an account, a verified email address and an activated license. Start once with 25 free items for Crawlune on one site; no credit card is needed for the trial.
Small pack
$19one-time purchase
100 generated items
One site · Adds to your balance; no automatic renewal
Choose 100 itemsSite pack
$79one-time purchase
500 generated items
One site · Adds to your balance; no automatic renewal
Choose 500 itemsWhat uses an item? An opening rewrite uses one item, a heading rewrite uses one, and a FAQ set for one page uses one. All three on a page use three items. Successful suggestions consume items even if you discard them or later undo them. Failed or declined generation does not consume an item.
Packs add items to your balance on one site. They do not renew automatically and have no calendar expiry while the service remains available. Saved output and unused purchased items remain if generation pauses for a spending-safety review. Contact support for a review; buying another pack is not the remedy for a safety pause.
Review every result before applying it. Applying or undoing saved results does not buy or generate more items. Read the service terms. For a safety pause, contact Matic for a review.
- AI agent controls, set individually
- 6AI agent controls, set individually
- Extractability score per page
- 0–100Extractability score per page
- Audit, llms.txt & crawler controls
- FreeAudit, llms.txt & crawler controls
- Free and open source
- GPLFree and open source
What is built today
Free audits. Optional hosted rewrites.
Each capability below is implemented and tested in the plugin as it stands. Hosted rewriting also works for activated licenses; a verified account can start with 25 free items once on one site.
Built
Per-agent AI crawler control
Six agent controls across OpenAI, Anthropic, Perplexity and Google, with training and retrieval purposes kept separate. Google-Extended is a permission token rather than a crawler. Crawlune emits denials without narrowing a wildcard rule defined elsewhere in robots.txt.
Built
Extractability audit, per page
Scores each page 0–100 across six signals: whether it opens with a liftable answer, whether it cites external sources, whether it quotes statistics, whether headings ask questions, whether it exposes a modified date, and whether it is too thin to be worth quoting.
Built
Site-wide visibility report
Median score, a count per weakness, and the weakest pages ranked — so the next thing to fix is the page a fix will move, not whichever one you happened to open.
Built
llms.txt, generated from real content
Both llms.txt and llms-full.txt, built from what the site actually publishes rather than hand-maintained. Worth knowing: llms.txt is a convention for helping agents find readable content. Publishing it does not guarantee crawling, ranking or citations.
Built
Score decomposition, not a number to trust
The weight of every signal is exposed, so the admin screen can break a score down instead of asking you to take it on faith. A score a reader cannot decompose is one they have to believe, and this product does not get to publish those.
Built
Admin screen and REST surface
The visibility report has a screen in wp-admin and authenticated REST routes behind real capability checks, so the audit is scriptable as well as readable.
Activated licenses
Review AI rewrites before applying
Compare suggested answer blocks, headings and grounded FAQ results with your current content. Apply approved changes and undo a run from the journal. Hosted rewriting requires an activated license; a verified account can start with 25 free items once on one site.
Try it without installing anything
Free tools and guides
The checker runs the same analysis as the plugin's audit, against a public URL instead of your posts table. No signup.
9 pages
Documentation
Every component of the extractability score and how each is measured, what llms.txt is and is not, what a rewrite may never change — and the one thing this product cannot tell you.
Explore6 tools
Free tools
Run the same extractability checks against any public URL, in the browser, with no signup and no plugin installed.
Explore5 guides
Guides
How answer engines pick sources, what the published research supports, and which of it you can actually act on.
ExploreBuild status
What ships, and what doesn't
Including the things this product will not do at all, which in a category this noisy is the more useful list.
Available on WordPress.orgPlugin v0.65.4
Crawlune is available as a free plugin on WordPress.org. Crawler controls, the content audit, reports, llms.txt and structured data run locally. Hosted rewriting is enabled for activated licenses: answer blocks, headings and grounded FAQ results have been verified through generation, review, apply and undo. Citation tracking is not included.
Implemented and tested
- AI crawler access control, per agent, with training and retrieval separated
- Extractability audit across six signals, scored 0–100 per page
- Site-wide visibility report: median score, per-weakness counts, weakest pages
- llms.txt and llms-full.txt generated from real content
- Per-page structured data, where no SEO plugin already provides it
- Answer-block rewriting, reviewed as a word-level diff before anything is applied
- Heading rewriting toward the question a section answers, preserving every heading's level and link address
- Generated FAQ data, where every proposed answer has to be text already on the page
- Applying a rewrite without breaking block markup, and reverting a run
- Admin screens and REST routes
- Licensing, metered in items, on the shared WP Shelf platform
Not available
- Citation tracking — whether you are actually quoted by a given engine
How generated items are counted
The audit, llms.txt and crawler controls are free without an account. One rewritten opening, one rewritten heading, or one FAQ set for a page uses one item each. Successful suggestions consume items even if discarded or undone; failed or declined generation does not. Purchased items have no calendar expiry while the service remains available. A spending-safety review can pause generation without removing unused purchased items or saved output.
FAQ
Questions, answered
Crawlune is a WordPress plugin for AI visibility: making a site legible, accessible and quotable to answer engines. It does four things — controls AI crawler access per agent, audits whether pages are extractable, generates a machine-readable llms.txt summary, and reports which structured-data types a page already declares. All of that is implemented and tested. So is the metered half — answer-block rewriting, heading rewriting and generated FAQ data all select, dispatch, review, apply and revert — hosted rewriting is enabled for activated licenses. A verified account can start with 25 free items once on one site. Citation tracking is not built. The free plugin is available on WordPress.org.
No plugin can promise that, and Crawlune does not. Whether a given engine quotes a given page is not measurable from inside WordPress, so any product claiming it is asking you to take an unfalsifiable claim on trust. What Crawlune does is subtractive: it finds the reasons an engine would skip you — a blocked retrieval crawler, a page with no liftable answer, no external citations, no statistics, no machine-readable summary — and reports each as a count you can verify yourself.
Yes. Install Crawlune – AI Crawler Controls from WordPress.org. The audit, crawler controls, reports and llms.txt run locally without an account or licence. Hosted rewriting is enabled for activated licenses; a verified account can start with 25 free items once on one site. You can also try the AI Visibility Checker on this site without installing.
GPTBot is OpenAI’s training crawler; disallowing it requests that crawled content not be used to train its foundation models. OAI-SearchBot is for ChatGPT search. OpenAI says opted-out sites are excluded from search answers but may still appear as navigational links. These controls are independent, and robots.txt is a directive to cooperating crawlers rather than an access barrier. Crawlune records a purpose for each of its six agent controls and flags a blocked retrieval crawler as a misconfiguration.
llms.txt gives agents a curated guide to your site and links to readable content. It is a convention described at llmstxt.org, not a guarantee that a search or answer engine will crawl, rank or cite a page. Crawlune builds it from your published content so you can keep that guide current.
Aggarwal et al., GEO: Generative Engine Optimization (KDD 2024), which tested a range of content interventions and found that citing sources, adding quotations and adding statistics produced the largest visibility gains. Crawlune's audit weights those signals accordingly. It is a real result on a specific benchmark, not a guarantee that the same interventions will move your traffic.
Local audits, crawler controls and llms.txt are free without an account. Hosted rewriting starts with 25 free items once per verified customer for Crawlune, on one site. Add 100 items for $19 or 500 for $79 as a one-time purchase with no automatic renewal. An opening rewrite, heading rewrite or FAQ set for a page uses one item each. Successful suggestions consume items even if discarded or undone. Purchased items have no calendar expiry while the service remains available; a safety review can pause generation without removing unused purchased items or saved output.
No. It does no sitemaps, no redirects, no rank tracking and no keyword research, and it does not touch titles, meta descriptions or alt text — those belong to SnippetGrove, a separate WP Shelf plugin. Crawlune is about whether a machine reading your page can extract an answer from it and is allowed to fetch it at all.
WordPress 6.4 or later and PHP 8.1 or later. Crawlune is GPLv2-licensed.
Start with the free audit.
Install Crawlune from WordPress.org to audit your pages and manage crawler access. You can also check a public URL in the browser before installing.
No account or licence needed for the local auditAudit, llms.txt & crawler controls free on every tierGPLv2, like everything on the shelf