# robots.txt for karun99.github.io
# Optimized for search engines AND AI / answer engines (AEO)

# --- AI ANSWER-ENGINE CRAWLERS (explicitly allowed for AEO) ---

# OpenAI (ChatGPT, SearchGPT, GPTBot)
User-agent: GPTBot
Allow: /

# OpenAI search / discovery crawler
User-agent: OAI-SearchBot
Allow: /

# OpenAI chat interface crawler (ChatGPT browsing)
User-agent: ChatGPT-User
Allow: /

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

# Anthropic Claude web crawl
User-agent: Claude-Web
Allow: /

# Anthropic primary crawler
User-agent: anthropic-ai
Allow: /

# Google (including Google-Extended used by Gemini / AI Overviews)
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /logo.jpg

# Google's AI / Gemini crawler
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Allow: /

# Microsoft Bing + Copilot
User-agent: Bingbot
Allow: /

# Microsoft AI crawler (Copilot, Bing Chat)
User-agent: Microsoft-PagesRobot
Allow: /

User-agent: CopilotBot
Allow: /

# Meta AI (Llama)
User-agent: Meta-ExternalAgent
Allow: /

# Amazon (Alexa, AWS Bedrock training)
User-agent: Amazonbot
Allow: /

# Apple (Applebot, Siri + Apple Intelligence)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ByteDance (Doubao / Trae)
User-agent: Bytespider
Allow: /

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

# Diffbot
User-agent: Diffbot
Allow: /

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

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Baidu
User-agent: Baiduspider
Allow: /

# Yandex
User-agent: YandexBot
Allow: /

# Moz / general SEO tools
User-agent: MJ12bot
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: SemrushBot
Allow: /

User-agent: DotBot
Allow: /

# Rytr / other AI writing assistants
User-agent: rytr-crawler
Allow: /

# Neeva
User-agent: NeevaBot
Allow: /

# Consensus (research AI)
User-agent: ConsensusBot
Allow: /

# Scaled Inference / answer engines
User-agent: ScaledInferenceBot
Allow: /

# --- DEFAULT: allow all other crawlers (they may follow sitemap) ---
User-agent: *
Allow: /

# --- AI / LLM CONTEXT FILES FOR CRAWLERS ---
# The LLM-readable markdown index (llmstxt.org standard) is served on-demand.
# llms.txt is served for any crawler that requests it (not governed by User-agent here).

# --- SITEMAPS ---
Sitemap: https://karun99.github.io/sitemap.xml