# MuniMatters - robots.txt
# Allow major search engines, block scrapers and most LLM crawlers
# Updated: 2026-05-19
#
# === LLM / RAG / agentic AI vendors ===
# Free crawl access by AI bots (GPTBot, ClaudeBot, OAI-SearchBot, CCBot,
# anthropic-ai, Google-Extended, PerplexityBot, Bytespider, Meta-ExternalAgent,
# Applebot-Extended, etc.) remains disallowed below. The opt-in, licensed
# alternative is the paid /api/llm-summary endpoint, which returns clean
# markdown summaries of state guides, educational articles, case studies, and
# the glossary under a written attribution + 15-word direct-quote policy.
# Documentation: https://munisource-app.netlify.app/llm-friendly.html

# === Explicit allow: major search engines (incl. Yandex) ===
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

# === Explicit disallow: LLM crawlers + scrapers ===
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: OmniBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: ISSCyberRiskCrawler
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

# === Default: allow everything except API/internal paths ===
User-agent: *
Allow: /
Disallow: /api/
Disallow: /.netlify/
Disallow: /app
Disallow: /*?nocache=*

# === Sitemaps ===
Sitemap: https://munisource-app.netlify.app/sitemap.xml