Web & Page Intelligence API Documentation

Independent public-page reads for agents: Markdown conversion, schema extraction, change detection, metadata, displayed contacts, and sitemap indexes. Pages are fetched directly over HTTP. No browser session is used. Payment is the exact USDC price on Base with x402.

{
  "url": "https://example.com/"
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://example.com/",
  "finalUrl": "https://example.com/",
  "httpStatus": 200,
  "contentType": "text/html",
  "warnings": [
    "Embedded frames were not fetched."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://example.com/",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "Only the bytes from one public HTTP GET are read. JavaScript is not executed."
  ],
  "markdown": "# Example Domain\n\nThis domain is for use in documentation examples.",
  "contentHash": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/url-to-markdown" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "url": "https://example.com/"
}
JSON

{
  "url": "https://example.com/",
  "schema": [
    {
      "name": "heading",
      "type": "string",
      "selector": "h1"
    }
  ]
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://example.com/",
  "finalUrl": "https://example.com/",
  "httpStatus": 200,
  "contentType": "text/html",
  "warnings": [
    "A JSON-LD script could not be parsed."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://example.com/",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "Without a selector, a field is filled only from a JSON-LD property, a meta name or property, or the document title when the field name is title."
  ],
  "fields": [
    {
      "name": "heading",
      "type": "string",
      "value": "Example Domain",
      "warnings": [
        "2 elements matched; the first was used."
      ]
    }
  ]
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/structured-page-extract" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "url": "https://example.com/",
  "schema": [
    {
      "name": "heading",
      "type": "string",
      "selector": "h1"
    }
  ]
}
JSON

{
  "url": "https://example.com/",
  "previousMarkdown": "Previous snapshot",
  "previousRetrievedAt": "2026-11-01T18:00:00.000Z"
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://example.com/",
  "finalUrl": "https://example.com/",
  "httpStatus": 200,
  "contentType": "text/html",
  "warnings": [
    "Only the first 40 added or removed lines are listed."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://example.com/",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "The previous snapshot is supplied by the caller and is not stored."
  ],
  "changed": true,
  "previousRetrievedAt": "2026-11-01T18:00:00.000Z",
  "previousHash": "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb",
  "currentHash": "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "currentMarkdown": "# Example Domain\n\nThis domain is for use in documentation examples.",
  "changes": [
    {
      "kind": "removed",
      "text": "Previous snapshot"
    },
    {
      "kind": "added",
      "text": "Example Domain"
    }
  ]
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/page-change-detect" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "url": "https://example.com/",
  "previousMarkdown": "Previous snapshot",
  "previousRetrievedAt": "2026-11-01T18:00:00.000Z"
}
JSON

{
  "url": "https://example.com/"
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://example.com/",
  "finalUrl": "https://example.com/",
  "httpStatus": 200,
  "contentType": "text/html",
  "warnings": [
    "A canonical link was present but was not an http or https URL."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://example.com/",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "robots.txt was not fetched. Robots values come from the page meta tag and the X-Robots-Tag header."
  ],
  "title": "Example Domain",
  "description": "Illustrative description from the description meta tag.",
  "canonicalUrl": "https://example.com/",
  "language": "en",
  "robots": {
    "meta": "index,follow",
    "header": "noarchive"
  },
  "openGraph": {
    "title": "Example Domain",
    "description": "Illustrative description",
    "type": "website",
    "url": "https://example.com/",
    "image": "https://example.com/image.png",
    "siteName": "Example",
    "locale": "en"
  }
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/website-metadata-extract" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "url": "https://example.com/"
}
JSON

{
  "url": "https://example.com/"
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://example.com/",
  "finalUrl": "https://example.com/",
  "httpStatus": 200,
  "contentType": "text/html",
  "warnings": [
    "No publicly displayed email, telephone, or address was found in the fetched HTML."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://example.com/",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "Phone numbers are taken from tel: links and structured contact data, not from arbitrary digit strings."
  ],
  "emails": [
    "info@example.com"
  ],
  "phones": [
    "+1-202-555-0100"
  ],
  "addresses": [
    "123 Example Street, Example City"
  ]
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/website-contact-extract" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "url": "https://example.com/"
}
JSON

{
  "sitemapUrl": "https://www.sitemaps.org/sitemap.xml"
}

{
  "retrievedAt": "2026-11-02T18:00:00.000Z",
  "requestedUrl": "https://www.sitemaps.org/sitemap.xml",
  "finalUrl": "https://www.sitemaps.org/sitemap.xml",
  "httpStatus": 200,
  "contentType": "application/xml",
  "warnings": [
    "Only the first 100 URLs are returned."
  ],
  "sources": [
    {
      "source": "Public HTTP response",
      "url": "https://www.sitemaps.org/sitemap.xml",
      "retrievedAt": "2026-11-02T18:00:00.000Z"
    }
  ],
  "limitations": [
    "Listed page URLs are not fetched. Metadata is only what each sitemap entry contained."
  ],
  "kind": "urlset",
  "entryKind": "page",
  "truncated": false,
  "entries": [
    {
      "loc": "https://example.com/",
      "lastmod": "2026-11-01",
      "changefreq": "weekly",
      "priority": "0.8"
    }
  ]
}

curl -i -X POST "https://brainiac.software/api/v1/web-intelligence/sitemap-content-index" \
  -H 'content-type: application/json' \
  -H 'Idempotency-Key: <fresh-64-character-random-hex-key>' \
  --data-binary @- <<'JSON'
{
  "sitemapUrl": "https://www.sitemaps.org/sitemap.xml"
}
JSON