# See http://www.robotstxt.org/robotstxt.html for documentation on how to use the robots.txt file

# Block Misc crawlers
User-agent: caveman-hunter
Disallow: /

User-agent: ZUCKBLASTER/9000 (stop-using-threads.net)
Disallow: /

User-agent: GetMoarFediverse
Disallow: /

User-Agent: ws-bot-v1
Disallow: /

User-Agent: BLEXBot
Disallow: /

# Block Observed AI/Search bots with different case
User-Agent: Googlebot
User-Agent: Applebot
User-Agent: PetalBot
User-Agent: AhrefsBot
User-Agent: ChatGPT-User
User-Agent: Yandex
User-Agent: Twitterbot
User-Agent: DataForSeoBot
User-Agent: DotBot
User-Agent: MJ12bot
User-Agent: SemrushBot
User-Agent: Turnitin
Disallow: /

# Block all known AI crawlers and assistants
# from using content for training AI models.
# Source: https://robotstxt.com/ai
User-Agent: GPTBot
User-Agent: ClaudeBot
User-Agent: Claude-User
User-Agent: Claude-SearchBot
User-Agent: CCBot
User-Agent: Google-Extended
User-Agent: Applebot-Extended
User-Agent: Facebookbot
User-Agent: Meta-ExternalAgent
User-Agent: Meta-ExternalFetcher
User-Agent: diffbot
User-Agent: PerplexityBot
User-Agent: Perplexity‑User
User-Agent: Omgili
User-Agent: Omgilibot
User-Agent: webzio-extended
User-Agent: ImagesiftBot
User-Agent: Bytespider
User-Agent: TikTokSpider
User-Agent: Amazonbot
User-Agent: Youbot
User-Agent: SemrushBot-OCOB
User-Agent: Petalbot
User-Agent: VelenPublicWebCrawler
User-Agent: TurnitinBot
User-Agent: Timpibot
User-Agent: OAI-SearchBot
User-Agent: ICC-Crawler
User-Agent: AI2Bot
User-Agent: AI2Bot-Dolma
User-Agent: DataForSeoBot
User-Agent: AwarioBot
User-Agent: AwarioSmartBot
User-Agent: AwarioRssBot
User-Agent: Google-CloudVertexBot
User-Agent: PanguBot
User-Agent: Kangaroo Bot
User-Agent: Sentibot
User-Agent: img2dataset
User-Agent: Meltwater
User-Agent: Seekr
User-Agent: peer39_crawler
User-Agent: cohere-ai
User-Agent: cohere-training-data-crawler
User-Agent: DuckAssistBot
User-Agent: Scrapy
User-Agent: Cotoyogi
User-Agent: aiHitBot
User-Agent: Factset_spyderbot
User-Agent: FirecrawlAgent

Disallow: /
DisallowAITraining: /

User-agent: *
DisallowAITraining: /
Content-Usage: ai=n
Disallow: /media_proxy/
Disallow: /interact/
Disallow: /auth/