# robots.txt — HelloGrowthCRM (https://hellogrowthcrm.com)
# Public pages are fully crawlable by all search engines and AI systems.
# /search is noindexed via metadata AND disallowed here to prevent crawl budget waste.
# Last updated: 2026-03-30

# ──────────────────────────────────────────────
# GLOBAL RULE — allow everything by default
# ──────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /admin
Disallow: /reset-password
Disallow: /api/
Disallow: /cdn-cgi/
# /search is a client-side filtered view — noindexed & blocked to save crawl budget
Disallow: /search

# ──────────────────────────────────────────────
# MAJOR SEARCH ENGINES
# ──────────────────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Sogou
Allow: /

User-agent: Exabot
Allow: /

User-agent: ia_archiver
Allow: /

# ──────────────────────────────────────────────
# AI TRAINING & ANSWER-ENGINE CRAWLERS
# (explicitly allowed for LLM indexing and AI search)
# ──────────────────────────────────────────────

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Anthropic user/search variants (not matched by ClaudeBot — without these they fall under User-agent: * and hit Disallow: /search)
User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Google AI / Gemini
User-agent: Google-Extended
Allow: /

User-agent: Googlebot-AI
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Amazon / Alexa
User-agent: Amazonbot
Allow: /

# Meta / Facebook AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (used by many LLM training datasets)
User-agent: CCBot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Diffbot (structured data AI)
User-agent: Diffbot
Allow: /

# DuckDuckGo AI Assistant
User-agent: DuckAssistBot
Allow: /

# Brave Search AI
User-agent: Brave-AI
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

# Exa AI
User-agent: exa-crawler
Allow: /

# Webz / Webhose data AI
User-agent: Webzio-Extended
Allow: /

# Timpi AI search
User-agent: Timpibot
Allow: /

# iAsk AI
User-agent: iaskspider
Allow: /

# ──────────────────────────────────────────────
# SOCIAL & LINK PREVIEW CRAWLERS
# ──────────────────────────────────────────────
User-agent: LinkedInBot
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# ──────────────────────────────────────────────
# SITEMAP DECLARATION
# ──────────────────────────────────────────────
Sitemap: https://hellogrowthcrm.com/sitemap.xml