# Boomerang robots.txt
# Last updated: 2026-09-24
# Site: https://www.getboomerang.ai
# For an operational manifest for AI agents, see: /llms.txt

# --- Major AI Search + Assistant Crawlers (Allowed) ---

# OpenAI: ChatGPT browsing + search index
User-agent: GPTBot
Allow: /
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /

# Anthropic: Claude browsing + index
User-agent: ClaudeBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-SearchBot
Allow: /
User-agent: anthropic-ai
Allow: /

# Google: AI Overviews + Gemini grounding
User-agent: Google-Extended
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Amazon: Alexa, Q, Rufus
User-agent: Amazonbot
Allow: /

# Perplexity: search index + assistant
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

# Microsoft Copilot
User-agent: CopilotBot
Allow: /

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
User-agent: Meta-ExternalFetcher
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /
User-agent: cohere-training-data-crawler
Allow: /

# Common Crawl: feeds LLM training corpora
User-agent: CCBot
Allow: /

# ByteDance: Doubao + TikTok search
User-agent: Bytespider
Allow: /

# Webz.io: licenses news/web data to AI companies
User-agent: Omgilibot
Allow: /
User-agent: Omgili
Allow: /

# --- Known scrapers + bot networks (Blocked) ---
# These crawlers either ignore directives, train on content without permission,
# or are used for low-quality content harvesting.
# Note: blocking AhrefsBot and SemrushBot also stops our own Ahrefs and Semrush
# site audits from crawling us. Remove those two blocks if we run audits there.

User-agent: Diffbot
Disallow: /
User-agent: PetalBot
Disallow: /
User-agent: MJ12bot
Disallow: /
User-agent: AhrefsBot
Disallow: /
User-agent: SemrushBot
Disallow: /
User-agent: DotBot
Disallow: /
User-agent: BLEXBot
Disallow: /
User-agent: ImagesiftBot
Disallow: /

# --- Default policy (everyone else) ---
User-agent: *
Allow: /
Disallow: /company-data/
# Block Webflow CMS pagination noise (drops ~46 crawl-budget waste URLs from "Crawled - not indexed")
Disallow: /*?a41587fa_page=
Disallow: /*?cdb99cf2_page=

# Sitemap line is appended automatically by Webflow (sitemap auto-generation is on).

Sitemap: https://www.getboomerang.ai/sitemap.xml

Sitemap: https://www.getboomerang.ai/sitemap.xml