# robots.txt - bharat.law
# Last updated: 2026-06-14
#
# Policy: open to all good-faith crawlers, including AI answer engines.
# We explicitly allow the major LLM crawlers so that ChatGPT, Perplexity,
# Claude, Gemini and Apple Intelligence can read, retrieve, and cite
# bharat.law content - central to our AEO (Answer Engine Optimization)
# strategy.

# --- General web crawlers ---
User-agent: *
Allow: /

# --- AI / answer-engine crawlers (explicit allow) ---
# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

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

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl (training data for many LLMs)
User-agent: CCBot
Allow: /

# Meta / Llama
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

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

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

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

# Bytespider (ByteDance / TikTok)
User-agent: Bytespider
Allow: /

# DuckDuckGo
User-agent: DuckAssistBot
Allow: /

# --- Discovery surfaces ---
Sitemap: https://bharat.law/sitemap.xml