AgentCheck

Is your site ready for AI agents?

People ask ChatGPT, Claude and Perplexity what they used to google. Check whether those assistants can read your site, quote it and link to it. It takes under a minute.

Quick runs without a browser. Full check adds browser-based checks and needs an account.

What an AI reads before it reads you

An AI answer cites a handful of sources. Four things decide whether your site can be one of them, and the score weighs them like this.

  • llms.txt is a table of contents for models

    30%

    A plain markdown file at the root that points to your important pages, plus markdown versions of those pages that a page links to and serves to agents that ask for markdown. A young standard, and ten minutes of work.

  • robots.txt says who may come in

    20%

    AI crawlers have their own names and obey robots.txt, which can now also say what they may do with your pages. Plenty of sites block them by accident with a rule copied years ago, or hide pages with a stray noindex, and a sitemap with dead links sends them nowhere. Your old robots.txt may not be a fan of ChatGPT.

  • Structure tells it what the page is

    25%

    One h1, headings in order, a canonical URL, a description and a language, JSON-LD and OpenGraph, and real content in the HTML itself, not only after JavaScript runs.

  • Buttons with names let agents act

    25%

    Browser agents book, buy and fill in forms. A div that pretends to be a button, or a captcha on a plain page, stops them. Agents cannot click on vibes.

25 checks in 4 categories, each based on a published standard. A full check also opens the page in a real browser and covers up to 10 pages of the site; every report looks for 13 agent protocols, and the fix files come from your own pages. See every check

How it works

  1. Paste a URL

    Start from any public page. We read it along with the site's robots.txt and llms.txt.

  2. We run the checks

    Quick reads your pages without a browser. Full also renders them in Chromium and needs an account.

  3. Fix what matters

    Every failed check comes with a remediation and, where possible, a snippet to copy.

Example report

A saved audit of vite.dev, shown the way you will see your own.

Check your site

80of 100

vite.dev

https://vite.dev

Redirected to https://vite.dev/

Example10 pagesChrome 155.0.8059.85
B

Agent protocolsChecked 13 protocols, none published.

not scored

Fair questions

Command line and CI

The CLI runs the same engine. Fail the build when the score drops.

$ npx agentcheck-dev https://vite.dev

 AgentCheck v0.2.0 — AI-Readiness Audit
 Target: https://vite.dev
 Browser: chrome 155.0.8059.85 (rendered in 4.0 s)

 [!] AI Manifests            75/100
     ✗ No markdown version of this page found
       Accept: text/markdown: answered with text/html
       https://vite.dev/index.md: HTTP 404
     ✗ The page does not answer Accept: text/markdown with markdown (answered with text/html)
 [!] Bot Access              77/100
     ✗ No Content-Signal found in robots.txt or the page's headers
     ⚠ Sitemap: 57 of 57 entries have no <lastmod>
     ⚠ The page limits what search and AI answers may quote
       1 element with data-nosnippet

 [!] Content & Semantics     73/100
     ⚠ Heading hierarchy has problems
       h1 → h6 ("Trusted by the world's best software teams")
       h2 → h5 ("Instant Server Start")
       h2 → h5 ("Flexible Plugin System")
     ✗ No structured data found
     ⚠ The meta description is 32 characters long (50–300 reads well as a link caption)
 [!] Agentic Actionability   80/100
     ⚠ 1 of 65 interactive elements have no accessible name (2%)
       link: <a.spsr-link.flex> href="https://www.cloudways.com/en/velocity.ph"

 [·] Agent protocols        not scored
     Checked 13 protocols, none published.

 ──────────────────────────────────────────────
 OVERALL AI SCORE: 76 / 100 [C]

$ npx agentcheck-dev https://vite.dev --threshold=85 --format=json # in CI
name: AI readiness
on: [push]
jobs: 
  agentcheck: 
    runs-on: ubuntu-latest
    steps: 
      - run: npx agentcheck-dev https://your-site.com --threshold=85 --format=json

agentcheck-dev on npm

Badge

Share a report and show the score in your README.

## Status

[![AI Ready: 80/100](<badge url>)](<report url>)
<a href="<report url>"><img src="<badge url>" alt="AI Ready: 80/100"></a>

Preview

Status

AI Ready: 80/100AI ReadyAI Ready80/10080/100

Check your site now

A quick check is free, needs no account and takes under a minute.

Quick runs without a browser. Full check adds browser-based checks and needs an account.