# robots.txt for SOMA
# Location: https://soma.himitsu8.ai/robots.txt
# Purpose: Allow search engines, AI crawlers, LLM retrieval agents, answer engines, and enterprise AI assistants to discover and access SOMA public content.
#
# Cross-linked LLM discovery files:
# SOMA compact LLM context: https://soma.himitsu8.ai/llms.txt
# SOMA full LLM context: https://soma.himitsu8.ai/llms-full.txt
# SOMA sitemap: https://soma.himitsu8.ai/sitemap.xml
# Company compact LLM context: https://himitsulab.com/llms.txt
# Company full LLM context: https://himitsulab.com/llms-full.txt
#
# Policy intent: permit crawling, indexing, AI retrieval, and LLM context discovery for public SOMA pages and public LLM context files.
# Note: xAI/Grok did not have a stable official robots.txt user-agent token confirmed in the public sources checked when this file was prepared; User-agent:* permits access for Grok or future AI agents that respect standard robots.txt rules.

User-agent: *
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /robots.txt
Allow: /sitemap.xml

# OpenAI crawlers and user-triggered retrieval
User-agent: OAI-SearchBot
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude crawlers and user-triggered retrieval
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Google Search, Gemini, Vertex AI, and related Google crawlers
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: GoogleOther-Image
Allow: /

User-agent: GoogleOther-Video
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

# Microsoft / Bing and Copilot ecosystem
User-agent: bingbot
Allow: /

User-agent: BingPreview
Allow: /

User-agent: msnbot
Allow: /

# Perplexity and answer-engine retrieval
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple, Amazon, Common Crawl, Meta, You.com, ByteDance and other search / AI retrieval crawlers
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: YouBot
Allow: /

# Sitemap for search and AI discovery
Sitemap: https://soma.himitsu8.ai/sitemap.xml