The web,
rebuilt for AI.
Lyrenth continuously indexes the open web and returns every page as a clean, structured AIDocument: the signal your agents need, without the markup they don't.
From Wikipedia, the free encyclopedia Methods for indexing the Internet **Web indexing**, or **Internet indexing**, comprises methods for indexing the contents of a [website](https://en.wikipedia.org/wiki/Website) or of the [Internet](https://en.wikipedia.org/wiki/Internet) as a whole. Individual websites or [intranet…
Signal,
not markup.
Every crawl of raw HTML drags in navs, ads, cookie walls, scripts, and trackers. Models pay, in tokens, latency, and dollars, to parse junk before reaching a single useful sentence.
An indexed page is different: rendered, cleaned, normalized, and rewritten into one canonical document a model reads in one pass. Lyrenth removes the noise once, for everyone.
An index,
not another scraper.
Every read resolves against the shared index, not the origin. When a thousand agents request the same URL, the origin sees one fetch: everyone else is served from cache in milliseconds. When freshness matters, force_refresh re-indexes on demand.
One canonical AIDocument per URL. Written once, read by everyone: shared infrastructure, not a per-customer scrape.
The open web, crawled on our schedule. Readers ask for the latest; Lyrenth fetches and serves it from the index.
A standing index sits between the two. Rendered, cleaned, normalized, and held.
Every reader resolves against the index and is answered in milliseconds.
The open web, crawled on our schedule. Readers ask for the latest; Lyrenth fetches and serves it from the index.
One canonical AIDocument per URL. Written once, read by everyone: shared infrastructure, not a per-customer scrape.
A standing index sits between the two. Rendered, cleaned, normalized, and held.
Every reader resolves against the index and is answered in milliseconds.
A stable contract
for every URL.
Send any public URL, get one AIDocument back: the same grouped JSON envelope every time, versioned forever. Validate against the public JSON Schema.
Every system that
reads the web.
If it consumes web data, it runs better on clean AIDocuments than on raw HTML.
What famous pages cost,
raw vs indexed.
Every row is a real page read through the index, with token economics reported by the API itself. Reproducible with one call.
| Page | Raw HTML tokens | AIDocument tokens | Smaller | Saved |
|---|---|---|---|---|
| Stripe API reference | 307,902 | 2,000 | 154x | 99.4% |
| Vercel Functions docs | 237,390 | 2,149 | 110x | 99.1% |
| Cloudflare Workers docs | 94,963 | 1,377 | 69x | 98.5% |
| GitHub REST API quickstart | 88,614 | 4,876 | 18x | 94.5% |
| Kubernetes Pods concepts | 131,977 | 7,475 | 18x | 94.3% |
Read the web like a machine.
Get an API key and pull your first AIDocument in under a minute. Web-scale, structured, and live.