# Manashid Economic Consulting — robots.txt
# Search engines: ALLOWED. AI training/scraping bots: BLOCKED.

# ---------- Search engines (allowed) ----------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Applebot
Allow: /

# ---------- AI training & LLM scrapers (blocked) ----------

# OpenAI — model training crawler
User-agent: GPTBot
Disallow: /

# OpenAI — ChatGPT browse / live retrieval
User-agent: ChatGPT-User
Disallow: /

# OpenAI — search index
User-agent: OAI-SearchBot
Disallow: /

# Google — AI training (Bard / Vertex AI / Gemini)
User-agent: Google-Extended
Disallow: /

# Anthropic — Claude crawlers
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Common Crawl (used by many AI training datasets)
User-agent: CCBot
Disallow: /

# Perplexity AI
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Disallow: /

# Amazon AI
User-agent: Amazonbot
Disallow: /

# Meta / Facebook AI
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: meta-externalagent
Disallow: /

# Apple AI training
User-agent: Applebot-Extended
Disallow: /

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

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

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

# Diffbot
User-agent: Diffbot
Disallow: /

# Omgili (data licensing for AI)
User-agent: omgili
Disallow: /

User-agent: omgilibot
Disallow: /

# ImagesiftBot (image AI training)
User-agent: ImagesiftBot
Disallow: /

# AI2 (Allen Institute)
User-agent: AI2Bot
Disallow: /

User-agent: Ai2Bot-Dolma
Disallow: /

# Timpi
User-agent: TimpiBot
Disallow: /

# Webz.io (AI data brokers)
User-agent: Webzio-Extended
Disallow: /

# Scrapy / generic AI scrapers
User-agent: Scrapy
Disallow: /

# ---------- Default rule ----------
# Allow everything else (e.g. social previews, well-behaved crawlers)
User-agent: *
Allow: /

Sitemap: https://manashidkw.com/sitemap.xml