# Voxa robots.txt
# Public website is fully open to search and AI crawlers.

User-agent: *
Allow: /

# --- AI / LLM crawlers (explicitly allowed) ---
# These bots fetch pages to ground answers in chat assistants and AI search.

# OpenAI (ChatGPT browsing, training, and search)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

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

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (Gemini / AI Overviews training opt-in)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

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

# Meta / Bytedance AI crawlers
User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

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

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

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

# Diffbot (knowledge graph)
User-agent: Diffbot
Allow: /

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