{"domain":"canicrawl.com","status":"valid","tier":"listed","authority":45,"verified":false,"title":"Canicrawl","summary":"A daily-updated census of AI-crawler access across 1020 major websites: which sites allow, restrict, or block 32 AI user agents (robots.txt), and which publish llms.txt. You are reading the llms.txt of a site that tracks llms.txt — welcome.","country":"US","country_source":"ip","publisher_country":null,"publisher_country_source":null,"hosting_country":"US","llms_txt":"https://canicrawl.com/llms.txt","llms_full_txt":"https://canicrawl.com/llms-full.txt","last_checked":"2026-10-26T00:26:23.052Z","agent_terms":null,"categories":["data-analytics"],"capabilities":[],"inferred_tags":["ai crawler access","robots.txt","llms.txt census","bot policy","ai user agents"],"audience":"mixed","agent_uses":["download_data","call_api","search_content"],"language":"en","platform_generated":false,"agent_summary":"Daily census of AI-crawler access policies (robots.txt) and llms.txt publication across 1020 major websites, with JSON data, stats, and changelog feeds.","llms_txt_cached":"https://agentwebmap.com/v1/domain/canicrawl.com/llms.txt","agentic":"interface","section_keys":["data","reuse"],"section_partial":false,"section_indexed_at":"2026-10-26T00:26:37.381Z"}