We Audited 25 Global SaaS Platforms for llms.txt v2: Here is What We Found

GrowNexus audited 25 major SaaS platforms to measure industry adoption of the llms.txt v2 specification, which was formally updated in August 2026 to add <link rel="describedby"> tags. The team found that the most significant operational issue is treating llms.txt as a raw sitemap dump, since files over 50KB consume 15,000+ tokens before an agent executes a single tool call, causing aggressive truncation. GrowNexus released the complete dataset and analysis scripts under a CC BY 4.0 license.

When the llms.txt proposal emerged as a standard to help LLMs and autonomous agents navigate web documentation efficiently, it promised an alternative to messy HTML scraping. In August 2026, the specification was formally updated to v2 , introducing two major changes: <link rel="describedby" tags. Our research team at GrowNexus https://grow-nexus.com audited 25 major SaaS platforms to measure how the industry is actually adopting the standard. We examined 25 prominent platforms across developer tooling, CMS, infrastructure, and productivity software: llms.txt file. rel="describedby" : The most significant operational issue discovered is using llms.txt as a raw sitemap dump. When autonomous agents like Claude Code, Codex, or Hermes parse context, scratchpads are token-budgeted. Files over 50KB consume 15,000+ tokens before the agent executes a single tool call, resulting in aggressive truncation. A well-architected llms.txt should act as a curated index of core endpoints—not a full site mirror. We have released the complete dataset and analysis scripts under the CC BY 4.0 license: How is your engineering team approaching llms.txt implementation for your APIs?