# infinivoai.eu — robots.txt
# Everything here is public marketing content. We WANT it read, indexed,
# retrieved, and cited — by search engines and by AI assistants alike.

# ---------------------------------------------------------------------------
# Default: everything open.
# ---------------------------------------------------------------------------
User-agent: *
Allow: /

# ---------------------------------------------------------------------------
# AI answer engines — explicitly allowed.
# These are named individually because several of them ignore or de-prioritise
# a bare wildcard, and because an explicit Allow is the only unambiguous
# signal that this content may be retrieved and cited.
# ---------------------------------------------------------------------------

# OpenAI — ChatGPT search index, user-initiated fetches, and training
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

# Anthropic — Claude search, user-initiated fetches, and training
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google — Gemini grounding and AI Overviews
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

User-agent: FacebookBot
Allow: /

# Microsoft Copilot / Bing generative
User-agent: bingbot
Allow: /

# Others that feed retrieval corpora
User-agent: Amazonbot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

User-agent: Diffbot
Allow: /

User-agent: Timpibot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: MistralAI-User
Allow: /

# ---------------------------------------------------------------------------
# Link-preview / unfurl agents — must stay open or shared links render bare.
# ---------------------------------------------------------------------------
User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: Discordbot
Allow: /

User-agent: TelegramBot
Allow: /

# ---------------------------------------------------------------------------
# Machine-readable summaries for LLM retrieval.
# ---------------------------------------------------------------------------
# /llms.txt      — condensed, structured overview of this business
# /llms-full.txt — the full corpus in one plain-text file

# ---------------------------------------------------------------------------
# Live MCP server, explicitly allowed.
# ---------------------------------------------------------------------------
# /mcp — a Model Context Protocol endpoint over streamable HTTP, and, to a
# browser or a crawler, the human-readable page documenting it. An assistant
# that speaks MCP should connect to it rather than scrape the text files above.
User-agent: *
Allow: /mcp

Sitemap: https://infinivoai.eu/sitemap.xml