Skip to content
OpenLLM logo

How AI assistants read openllm.sh

What a machine reading this site receives: identity files, schema, crawler policy, the entity behind the name. Read weekly by a crawler, no model call. For the people who run OpenLLM; the catalogue page is for the people who choose it.

Run the full check on openllm.sh

← Back to OpenLLM

Atlas Readinesssweptchecked 2026-10-28

54/100

  • Entity0/25
  • Machine-readable31.5/35
  • Retrieval access17/20
  • Footprint5.6/20
all four parts read
What to fix firstfound in our 2026-10-28 check

7 retrieval crawlers are blocked on /get-started, /keys, /overview, /providers, /vault

high

The heaviest thing this check found wrong, named in the words our fix list uses. Read off the site itself, not from a model.

Usedsweptchecked 2026-10-28

not read yet

Does anybody use it: audience (Tranco list, Chrome UX report, estimated organic visits), installs from registries, referring domains. Never votes, never reviews.

  • Audiencenot read
  • Installsnot read
  • Referencesnot read
nothing read yet
Alivesweptchecked 2026-10-28

90/100

Is anybody home: the homepage answers, the content moves, something ships, somebody hires. Each part a dated reading from a public place; a part not read is left out and the total rescaled.

  • Answers30/30
  • Content moves21.9/30
  • Ships25/25
  • Hiringnot read
out of 85 of 100 points — hiring not read
Against the fieldsweptreadiness, out of 100
  • OpenLLM54
  • Atlas medianof 26944 rated61
What our weekly check readsweptchecked 2026-10-28
  • Retrieval botspartialverify

    Whether the bots that decide citations are let in. Training bots are a separate list and are not counted here.

  • llms.txtyesverify

    A plain-text index at /llms.txt. Optional; read by some tools.

  • Organization schemayes

    schema.org Organization markup on the homepage, which is what a resolver reads a company's name and links from.

  • Wikidata itemnone

    Matched on the official website, never on the name. The substrate under the knowledge graph an engine resolves names against.

  • Server-rendered words620swept

    What a reader without JavaScript receives from the homepage.

  • Identity score90/100swept

    The analyzer's crawl-only section, 0-100: identity files, schema, crawler policy, sitemap. Not the analyzer score.

  • Footprint12 GitHub stars
Position in Developer toolsswept4141 checked

90/100

identity score

0identity score, 0-100100
50th percentile of 4141 · median 90

Not measured with the analyzer.

The full run asks four engines about this company by name. It runs on request, not on a schedule.

Questions this page answers
  • What is OpenLLM's Atlas Readiness?

    54 of 100 on 2026-10-28, computed from four parts — entity, machine-readable, retrieval access, footprint — all four parts read.

  • Does OpenLLM let AI retrieval bots in?

    Partly. On 2026-10-28, openllm.sh fenced some paths from retrieval crawlers.

  • Does OpenLLM publish an llms.txt?

    Yes: openllm.sh/llms.txt was present on 2026-10-28.

  • Is OpenLLM a Wikidata entity?

    No item whose official website is openllm.sh was found on 2026-10-28.

How to read a row

swept
Read by a crawler: HTTP and parsing, no model call. Every tool, every week.
measured
The full analyzer run, asked of four engines. Shown only where the company agreed to show it.

Can a retrieval engine find, resolve and quote this site? Four parts, each read by the sweep, each shown beside the total.

Entity 25 · Machine-readable 35 · Retrieval access 20 · Footprint 20

A part that was never read is left out and the total is rescaled to what was. It is never counted as zero.

Run the full check on openllm.sh →