# robots.txt for SaaS Hive — explicit allow for AI crawlers (GEO best practice)
# Reference: https://llmstxt.org/ + https://platform.openai.com/docs/bots

# --- Search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# --- Social previews ---
User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Discordbot
Allow: /

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

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# --- Perplexity ---
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# --- Apple Intelligence ---
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# --- Common Crawl (powers many LLM training sets) ---
User-agent: CCBot
Allow: /

# --- Other AI crawlers ---
User-agent: cohere-ai
Allow: /

User-agent: Cohere-AI
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: MistralAI-User
Allow: /

# --- Default ---
User-agent: *
Allow: /

# --- Disallow sensitive / probed paths ---
# Environment & secrets
Disallow: /.env
Disallow: /env
Disallow: /.aws
Disallow: /aws_secret_access_key
Disallow: /proc/self/environ
Disallow: /etc/passwd
Disallow: /etc/shadow
Disallow: /.ssh
Disallow: /secret
Disallow: /private
Disallow: /credentials
Disallow: /config
Disallow: /configuration

# API & auth endpoints
Disallow: /api/
Disallow: /auth/
Disallow: /stripe
Disallow: /api/credentials

# Admin probes
Disallow: /admin
Disallow: /administrator
Disallow: /wp-admin
Disallow: /wp-login
Disallow: /wp-config
Disallow: /wp-content/uploads
Disallow: /xmlrpc.php

# Version control & dev tooling
Disallow: /.git
Disallow: /.svn
Disallow: /.hg
Disallow: /debug
Disallow: /.debug
Disallow: /console
Disallow: /cgi-bin

# Server config probes
Disallow: /.htaccess
Disallow: /.htpasswd
Disallow: /server-status
Disallow: /server-info
Disallow: /phpinfo
Disallow: /info.php

# Data & backup probes
Disallow: /backup
Disallow: /database
Disallow: /dump
Disallow: /sql
Disallow: /db

# Framework internals
Disallow: /__
Disallow: /_debug

Sitemap: https://saashive.com/sitemap.xml