{"slug": "we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found", "title": "We Audited 25 Global SaaS Platforms for llms.txt v2: Here is What We Found", "summary": "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.", "body_md": "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.\n\nIn August 2026, the specification was formally updated to **v2**, introducing two major changes:\n\n`<link rel=\"describedby\">` tags.\nOur research team at **[GrowNexus](https://grow-nexus.com)** audited 25 major SaaS platforms to measure how the industry is actually adopting the standard.\n\nWe examined 25 prominent platforms across developer tooling, CMS, infrastructure, and productivity software:\n\n`llms.txt` file.`rel=\"describedby\"`):\nThe most significant operational issue discovered is using `llms.txt` as a raw sitemap dump. \n\nWhen 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.\n\nA well-architected `llms.txt` should act as a **curated index** of core endpoints—not a full site mirror.\n\nWe have released the complete dataset and analysis scripts under the CC BY 4.0 license:\n\nHow is your engineering team approaching `llms.txt` implementation for your APIs?", "url": "https://wpnews.pro/news/we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found", "canonical_source": "https://dev.to/grownexus/we-audited-25-global-saas-platforms-for-llmstxt-v2-here-is-what-we-found-218o", "published_at": "2026-09-19 06:09:55+00:00", "updated_at": "2026-09-19 06:54:27.320686+00:00", "lang": "en", "topics": ["agent-protocols", "ai-agents", "ai-crawlers", "structured-data", "developer-tools"], "entities": ["GrowNexus", "Claude Code", "Codex", "Hermes"], "alternates": {"html": "https://wpnews.pro/news/we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found", "markdown": "https://wpnews.pro/news/we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found.md", "text": "https://wpnews.pro/news/we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found.txt", "jsonld": "https://wpnews.pro/news/we-audited-25-global-saas-platforms-for-llms-txt-v2-here-is-what-we-found.jsonld"}}