LYRENTH
AgentsDocsPricingBenchmarksIndex statsAboutBlogFor site ownersStatusContact
For AI agents, chat apps, copilots and assistants

Stop building a web stack.
Start shipping your agent.

The web layer for your agent, already built. The crawlers, browsers, proxies, parsers and cache are running now. Send a URL, get clean text your model can read, with its source. Free while you build, paid when you grow.

  • no crawlers to run
  • no headless browsers
  • no parsers to fix
  • no cache to keep fresh

One call per page. Answers in milliseconds from the index, and up to 99.4% fewer input tokens than raw HTML on measured pages.

Where it fits

Three jobs
you probably recognise.

Lyrenth returns the page content. The answering, the researching and the embedding stay yours. Or start from something that already works: eleven ready-to-use agents, one command each, and the research one published on its own as lyrenth-research.

01Answer questions about a linkA user pastes a URL into your assistant and expects an answer about that page. Your model needs the page content. Lyrenth returns readable text and source information you can pass straight to it.POST /v1/aidocument
02Read the sources your research agent findsFinding links is the easy half. Your agent still needs usable content out of pages with different layouts. Lyrenth returns that content in the same shape every time, with the source it came from.OPEN SOURCE EXAMPLE
03Bring public pages into your knowledge baseFetching pages and cleaning HTML adds maintenance to your ingestion pipeline forever. Lyrenth handles that step, so your work stays on chunking, embedding and using the content.BATCH - 20 URLS PER CALL
What you plug into

Everything on the left is ours.
On your side: one call.

Crawling, rendering, cleaning and caching all happen before you ask. Most pages you request have already been read, so yours comes back in milliseconds and the site is never touched again. The more people read through Lyrenth, the more of the web is already waiting when you arrive. When freshness matters, force_refresh re-indexes on demand.

01 · Origins
one crawl →
02 · The standing index
→ every read
03 · Readers
crawl
crawl
crawl
Lyrenthindexing · live
AIDocuments in the index
POST/v1/aidocumentHIT

One canonical AIDocument per URL. Written once, read by everyone: the work happens on our side, the call happens on yours.

Freshness, per request
cache_firstforce_refreshyou choose
Autonomous agents
per-url · mcp
AI assistants
retrieve · cite
AI search & discovery
search · rank
RAG systems
embed · index
Model labs
corpus · bulk
Enterprise & research
pipeline · api

We crawl the open web and render the pages that need a browser. It runs without you, around the clock.

One standing index in the middle: cleaned, normalized, held, and shared by every reader.

Your side is one request. Send a URL, get the document back in milliseconds. Done.

01 · Origins
crawl
crawl

We crawl the open web and render the pages that need a browser. It runs without you, around the clock.

one crawl
02 · The standing index
Lyrenthindexing · live
AIDocuments in the index
POST/v1/aidocumentHIT

One canonical AIDocument per URL. Written once, read by everyone: the work happens on our side, the call happens on yours.

Freshness, per request
cache_firstforce_refreshyou choose

One standing index in the middle: cleaned, normalized, held, and shared by every reader.

every read
03 · Readers
Autonomous agents
per-url · mcp
AI assistants
retrieve · cite
AI search & discovery
search · rank
RAG systems
embed · index
Model labs
corpus · bulk
Enterprise & research
pipeline · api

Your side is one request. Send a URL, get the document back in milliseconds. Done.

Is not✕Raw crawling✕Scraping-as-a-service✕A normal search engine✕Another data broker
Is✓The AI-readable web index
AI-readable pages indexed
4,007,047,285
170,423,964
Indexed domains
4,003.0M
Pages audited
24h to 90d
Freshness, by plan
Real data, from the production API

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.

PageRaw HTML → AIDocumentRaw tokensAIDocumentSaved
Stripe API reference
154× smaller
307,9022,00099.4%
Vercel Functions docs
110× smaller
237,3902,14999.1%
Cloudflare Workers docs
69× smaller
94,9631,37798.5%
GitHub REST API quickstart
18× smaller
88,6144,87694.5%
Kubernetes Pods concepts
18× smaller
131,9777,47594.3%
Measured 2026-07-05 · cost basis $3.00 / 1M input tokens · grey is the raw page, teal is what the model readsAll 10 benchmarks →
One request, one document

The same shape,
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.

Full AIDocument schema in the docs →
POST/v1/aidocumentresolve any URL
GET/v1/read?url=…markdown, one GET
POST/v1/submitqueue for indexing
GET/v1/statspublic counter
GET/aidocument.schema.jsonthe contract
Quickstart: first call in a minute →
Check your own site

How does AI
actually read you?

AI cannot recommend what it cannot read. Paste your URL and see exactly what an agent receives from your page: how much of it is real content, what is missing, and what to fix. Most sites have never been checked.

Check your site →Free with an account. No card.
Try it

Try a page
your application needs to read.

No account for the first reads. Paste a URL, watch it resolve, and see what your model would receive: the same grouped JSON envelope every time, with the tokens it saved.

POST
from the cached index · site not contacted2,722 tokens · 89.0% saved
Web indexing - Wikipedia
en.wikipedia.org/wiki/Web_indexing

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…

lang entype Article1,556 words8 min readhas JSON-LD
Tokens saved
89.0%
24,734 → 2,722
AIDocument tokens
2,722
what the model reads
Origin fetches
0
shared, cross-caller cache
Served from
cached index
instant · fresh copy on demand
No account, one command
curl "https://api.lyrenth.com/v1/public/aidocument?url=https://en.wikipedia.org/wiki/Web_indexing"
Or add it to your agent
claude mcp add --transport http lyrenth https://api.lyrenth.com/mcp \
  --header "Authorization: Bearer $LYRENTH_API_KEY"

Ready to call it from your own code? The quickstart has the same request in nine languages, including Python, TypeScript and Go.

  • 25 reads an hour with no account.
  • 2,000 a month with a free key.
  • The first 1,000 to claim it get Starter, 20,000 a month, free for 90 days.
  • No card.
Get started

Point it at a URL and see.

Your first read takes about a minute. 2,000 a month free, no card, and nothing to install.