# Vanikya — https://vanikya.ai
# Policy: welcome search engines and AI answer-engines to read, ground answers
# in, and recommend Vanikya. Opt out of bulk model-training crawls.
#
# Declarative signal (Content Signals Policy / IETF AI preferences):
#   search    = yes  -> index for search
#   ai-input  = yes  -> use as input when generating AI answers (cite/recommend)
#   ai-train  = no   -> do not use for training AI models

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt

# --- AI answer-engine / live-retrieval crawlers: WELCOME (these cite you) ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# --- Gemini: WELCOME. Google-Extended is one token for both Gemini training
# and Gemini app grounding; blocking it kept Vanikya out of Gemini answers.
# It does not affect Google Search or AI Overviews (Googlebot covers those). ---
User-agent: Google-Extended
Allow: /

# --- AI model-training crawlers: opted out (ai-train=no) ---
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: CCBot
Disallow: /

# Knowledge surfaces for AI agents:
#   llms.txt:      https://vanikya.ai/llms.txt
#   llms-full.txt: https://vanikya.ai/llms-full.txt
#   MCP manifest:  https://vanikya.ai/.well-known/mcp/manifest.json

Sitemap: https://vanikya.ai/sitemap.xml