# =========================
# numeracle.com robots.txt
# Last updated: 2025-08-13
# =========================
# Base rules for all crawlers
User-agent: *
Disallow: /404
Disallow: /401
Disallow: /search
# Webflow editor parameter
Disallow: /*?edit=*
# Canonical sitemap
Sitemap: https://www.numeracle.com/sitemap.xml
# Canonical Host
Host: https://www.numeracle.com
# Crawl throttling where supported (Google ignores Crawl-delay; Bing/Yandex honor it)
User-agent: bingbot
Crawl-delay: 10
User-agent: yandex
Crawl-delay: 5
# -------------------------
# AI / LLM and preview bots
# -------------------------
# OpenAI
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
# Google AI data control (Gemini, Vertex AI use)
User-agent: Google-Extended
Allow: /
# Anthropic
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /
# Google Gemini crawler
User-agent: GeminiBot
Allow: /
# Perplexity
User-agent: PerplexityBot
Allow: /
# Common Crawl (used broadly in AI research)
User-agent: CCBot
Allow: /
# Apple (search/ML)
User-agent: Applebot
Allow: /
# Amazon
User-agent: Amazonbot
Allow: /
# Meta link preview
User-agent: FacebookExternalHit
Allow: /
# X/Twitter link preview
User-agent: Twitterbot
Allow: /
# ByteDance / TikTok
User-agent: Bytespider
Allow: /
# You.com
User-agent: YouBot
Allow: /
# SEO Crawler
User-agent: SemrushBot
Allow: /
Sitemap: https://www.numeracle.com/sitemap.xml