LYRENTH
HomePricingIntegrationsDocsBlogBenchmarksIndex statsAboutContact
Index stats

The AI-readable
web index, live.

Production truth, ticking: every counter below reads from the live index, where each page of the public web becomes one canonical, clean AIDocument. First the index; then what it delivers; then the audit of the raw web it replaces.

Indexed documents
1,182,913,702
Pages in the canonical index, counting live
Indexed domains
124,980,826
Distinct domains represented in the index
Audited pages
1,181,308,970
99.9% of indexed pages scored on seven signals
What the index delivers
Measured token reduction
94%
Median across the measured benchmark set, from the API's own economics
JS rendering absorbed
50%
Share of pages that need a headless browser; the index runs it so your agent never does
Corpus freshness
24h / 90d
Recrawl cadence by plan, Pro to Free; stale pages refresh on read
Before Lyrenth

The raw web, audited

This is the part the index replaces. Every page is scored on seven content signals measured on the SOURCE page as our crawler found it: the state of the raw web, not of what we serve. Averaged across the corpus, the raw web scores 5.5 / 10 on AI readability. Agents reading through the index never see these problems: they get the cleaned AIDocument, and the token difference is measured on the benchmarks page.

Structured data20% weight23%

Whether the page carries JSON-LD blocks (Article, Product, FAQPage…). Structured data lets agents extract facts without parsing prose.

Heading hygiene15% weight63%

Single H1, monotonic descent through H2 / H3. Predictable structure makes a page easier to skim and section.

Static renderability20% weight50%

Share of pages served without a headless-Chromium escalation. Static-renderable pages cost less and never arrive empty to first-pass scrapers.

Content density20% weight50%

Ratio of meaningful markdown to raw HTML. High density means most of the page is content, not nav / chrome / ads.

Title & description10% weight66%

Non-empty, sensible-length title and description that are not generic placeholders.

Open access10% weight99.9%

Share of indexed pages that reach readers (and agents) without paywall or login-wall markers. Paywalled pages are indexed and scored too, so this is a measured rate across the corpus, not a definition.

Content depth5% weight79%

Whether the page has enough words to be substantive on its own. Sub-stub pages get partial credit; pages with no body fail outright.

How to read this

What these numbers mean

For AI agent builders

A high site-wide structured-data percentage means agents can extract facts cheaply. Low static-renderability or density means more of your input tokens pay for headless rendering and chrome, not content. Lyrenth normalizes these into a single AIDocument shape regardless of how the source page is built.

Read the quickstart

For site owners

The signals above are exactly what Lyrenth measures per page on your verified domains. Verify a domain to see your own AI Readiness score on the dashboard, broken down page by page.

Verify a domain

Methodology: every audited page is scored on seven content signals, each 0.0 to 1.0. Per-page scores roll up to a domain average and a corpus-wide mean. Raw page content stays in our private index; only aggregate counts and means are public. Counters are live; signal aggregates recompute about every 10 minutes.