94 lines
2.4 KiB
Plaintext
94 lines
2.4 KiB
Plaintext
# from using content for training AI models.
|
||
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
|
||
User-Agent: bedrockbot
|
||
User-Agent: DeepSeekBot
|
||
User-Agent: GoogleAgent-Mariner
|
||
User-Agent: Gemini-Deep-Research
|
||
User-Agent: Google-NotebookLM
|
||
User-Agent: Google-Agent
|
||
User-Agent: GoogleAgent-URLContext
|
||
User-Agent: Google-Firebase
|
||
User-Agent: MistralAI-User
|
||
User-Agent: SemrushBot-FT
|
||
User-Agent: SemrushBot-ESI
|
||
User-Agent: AddSearchBot
|
||
User-Agent: bigsur.ai
|
||
User-Agent: Brightbot
|
||
User-Agent: Crawlspace
|
||
User-Agent: EchoboxBot
|
||
User-Agent: FriendlyCrawler
|
||
User-Agent: LinerBot
|
||
User-Agent: Panscient
|
||
User-Agent: Panscient.com
|
||
User-Agent: Poseidon Research Crawler
|
||
User-Agent: SBIntuitionsBot
|
||
User-Agent: TerraCotta
|
||
User-Agent: Thinkbot
|
||
User-Agent: Yak
|
||
User-Agent: YandexAdditional
|
||
User-Agent: YandexAdditionalBot
|
||
|
||
Disallow: /
|
||
DisallowAITraining: /
|
||
|
||
# Block any non-specified AI crawlers (e.g., new
|
||
# or unknown bots) from using content for training
|
||
# AI models, while allowing the website to be
|
||
# indexed and accessed by bots. These directives
|
||
# are still experimental and may not be supported
|
||
# by all AI crawlers.
|
||
User-Agent: *
|
||
DisallowAITraining: /
|
||
Content-Usage: ai=n
|
||
Content-Signal: search=yes, ai-input=no, ai-train=no
|
||
Allow: /
|