llms.txt files: 100 KB and over
In short
29 entries in the llms.txt Index are files in the size bucket 100 KB and over. The median file is 380 KB and the most common grade is B (17 of 29). 4 of 28 entries with a tested home page link the file from it. Each entry shows the file, the parse and the date read.
Crawl edition 2026-11-04, Ora reads 2026-11-05, page updated 2026-11-05. How the viewer, the index and the scores work.
29 published entries are files in the size bucket 100 KB and over. The median file is 380 KB. Grades: B 17, C 8, D 2, F 2. 4 of 28 entries with a tested home page link the file from it.
The Ora column is the cached score and grade from Ora's GET /api/score/{domain}, read 5 November 2026. "Not scored" means Ora answered 404 DOMAIN_NOT_SCANNED for the domain. This site asked for cached scores only and never requested a scan. Ora's report page for a domain is ora.ai/score/ followed by the domain, for example ora.ai/score/telnyx.com.
| Host | The file opens with | Structure grade | Size | Links | Ora score |
|---|---|---|---|---|---|
| upstash.com | Upstash Documentation | C | 184 KB | 1,555 | 88 A |
| gitbook.com | GitBook Documentation | C | 128 KB | 753 | 86 A |
| elevenlabs.io | ElevenLabs Documentation | B | 235 KB | 1,508 | 86 A |
| redocly.com | Redocly | B | 125 KB | 1,152 | 69 C |
| salesforce.com | No H1 | F | 997 KB | 3,777 | 51 C |
| twilio.com | No H1 | D | 2.4 MB | 7,679 | 85 B |
| dropbox.com | Dropbox | B | 204 KB | 829 | 66 C |
| unity.com | Unity | B | 923 KB | 2,469 | 61 C |
| docs.cursor.com | An HTML page at /llms.txt | F | 571 KB | 0 | 42 D |
| unity3d.com | Unity | C | 926 KB | 2,469 | 21 F |
| sourceforge.net | SourceForge | B | 1.9 MB | 2,022 | 69 C |
| datadoghq.com | Datadog | B | 583 KB | 2,431 | 69 C |
| zendesk.com | Zendesk.com | B | 724 KB | 3,136 | 79 B |
| okta.com | Okta and Auth0 Platforms | B | 224 KB | 1,526 | 64 C |
| dynatrace.com | LLM documentation for www.dynatrace.com | B | 178 KB | 1,107 | 82 B |
| taboola.com | Taboola.com | B | 272 KB | 1,831 | 71 B |
| selectel.ru | Selectel | B | 497 KB | 1,664 | not scored |
| mailchimp.com | Mailchimp - Complete Web Content Analysis | B | 515 KB | 990 | 65 C |
| instructure.com | Instructure | B | 563 KB | 4,170 | 44 D |
| clever.com | Clever | C | 202 KB | 647 | 52 C |
| singular.net | Singular – end-to-end attribution and analytics platform | B | 219 KB | 927 | 46 D |
| kir2kos.net | سکس ایرانی | دانلود فیلم پورن ایرانی و سوپر وطنی - بکن تو | D | 472 KB | 1,394 | not scored |
| xorgasmo.com | XOrgasmo.com | B | 638 KB | 2,868 | not scored |
| sendbird.com | Sendbird | B | 276 KB | 1,112 | 63 C |
| posthog.com | PostHog | B | 473 KB | 4,616 | 86 A |
| livechatinc.com | LiveChat - The Best AI Live Chat Software for Business | LiveChat.com | C | 232 KB | 933 | not scored |
| riskified.com | Riskified | C | 117 KB | 396 | 52 C |
| duosecurity.com | Cisco Duo | C | 261 KB | 1,122 | not scored |
| walkme.com | WalkMe | C | 380 KB | 1,466 | 54 C |
Back to the full index. Filters are plain links: each one is its own page, so an agent can follow them without a form.
Sources
- llms.txt proposal (llmstxt.org) https://llmstxt.org/, read 4 November 2026
- The crawl dataset (this site) https://agentreadyhtml.com/data/, read 4 November 2026
Last reviewed 5 November 2026