# VoicePing Robots.txt
# Last updated: 2026-10-19

# Standard Search Engine Crawlers
User-agent: Googlebot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Bingbot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Applebot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# ============================================
# AI/LLM CRAWLERS - SEARCH, USER RETRIEVAL AND TRAINING
# Access permission does not guarantee indexing, rankings or citations.
# ============================================

# OpenAI search indexing (independent of GPTBot training permission)
User-agent: OAI-SearchBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# User-initiated ChatGPT retrieval
User-agent: ChatGPT-User
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Anthropic training, user retrieval and search, respectively
# https://support.claude.com/en/articles/8896518
User-agent: ClaudeBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Claude-User
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Claude-SearchBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: anthropic-ai
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Perplexity Crawlers (https://docs.perplexity.ai/guides/bots)
User-agent: PerplexityBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Perplexity-User
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# ============================================
# MODEL DEVELOPMENT AND OTHER CONTENT USE (EXISTING ALLOW POLICY)
# Training access is a separate preference from search visibility.
# ============================================

# OpenAI Training
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Gemini training and grounding in Gemini Apps/Vertex AI.
# Google-Extended does not control Google Search inclusion or ranking.
User-agent: Google-Extended
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Apple AI Training
User-agent: Applebot-Extended
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Common Crawl (used by many AI projects)
User-agent: CCBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Meta/Facebook AI
User-agent: FacebookBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: meta-externalagent
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# ByteDance/TikTok
User-agent: Bytespider
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Amazon
User-agent: Amazonbot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Other AI Crawlers
User-agent: cohere-ai
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: AI2Bot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Diffbot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# ============================================
# SOCIAL MEDIA CRAWLERS (ALLOW for link previews)
# ============================================

User-agent: LinkedInBot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: Twitterbot
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

User-agent: facebookexternalhit
Allow: /
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# ============================================
# DEFAULT RULE
# ============================================

User-agent: *
Allow: /

# Disallow admin/private paths
Disallow: /admin/
Disallow: /private/
Disallow: /_*

# Sitemaps
Sitemap: https://voice-ping.com/sitemap.xml

# LLMs.txt for AI optimization
# See: https://voice-ping.com/llms.txt