1- # www.robotstxt.org/
2-
3- # List generated from https://darkvisitors.com/
4-
5- User-agent: cohere-ai
6- Disallow: /
1+ # https://github.com/ai-robots-txt/ai.robots.txt/blob/main/robots.txt
72
3+ User-agent: AI 2 Bot
4+ User-agent: Ai 2 Bot-Dolma
5+ User-agent: aiHitBot
6+ User-agent: Amazonbot
7+ User-agent: Andibot
88User-agent: anthropic-ai
9- Disallow: /
10-
9+ User-agent: Applebot
10+ User-agent: Applebot-Extended
11+ User-agent: bedrockbot
12+ User-agent: Brightbot 1 .0
1113User-agent: Bytespider
12- Disallow: /
13-
1414User-agent: CCBot
15- Disallow: /
16-
15+ User-agent: ChatGPT-User
16+ User-agent: Claude-SearchBot
17+ User-agent: Claude-User
18+ User-agent: Claude-Web
19+ User-agent: ClaudeBot
20+ User-agent: cohere-ai
21+ User-agent: cohere-training-data-crawler
22+ User-agent: Cotoyogi
23+ User-agent: Crawlspace
24+ User-agent: Diffbot
25+ User-agent: DuckAssistBot
26+ User-agent: EchoboxBot
1727User-agent: FacebookBot
18- Disallow: /
19-
28+ User-agent: facebookexternalhit
29+ User-agent: Factset _spyderbot
30+ User-agent: FirecrawlAgent
31+ User-agent: FriendlyCrawler
32+ User-agent: Google-CloudVertexBot
2033User-agent: Google-Extended
21-
22- User-agent: AdsBot-Google
23- Disallow: /
24-
34+ User-agent: GoogleOther
35+ User-agent: GoogleOther-Image
36+ User-agent: GoogleOther-Video
2537User-agent: GPTBot
26- Disallow: /
27-
28- User-agent: ChatGPT-User
29- Disallow: /
30-
31- User-agent: omgili
32- Disallow: /
33-
38+ User-agent: iaskspider /2.0
39+ User-agent: ICC-Crawler
40+ User-agent: ImagesiftBot
41+ User-agent: img 2 dataset
42+ User-agent: ISSCyberRiskCrawler
43+ User-agent: Kangaroo Bot
3444User-agent: meta-externalagent
35- Disallow: /
36-
37- User-agent: Amazonbot
38- Disallow: /
39-
45+ User-agent: Meta-ExternalAgent
46+ User-agent: meta-externalfetcher
47+ User-agent: Meta-ExternalFetcher
48+ User-agent: MistralAI-User /1.0
49+ User-agent: MyCentralAIScraperBot
50+ User-agent: NovaAct
51+ User-agent: OAI-SearchBot
52+ User-agent: omgili
53+ User-agent: omgilibot
54+ User-agent: Operator
55+ User-agent: PanguBot
56+ User-agent: Panscient
57+ User-agent: panscient .com
4058User-agent: Perplexity-User
41- Disallow: /
42-
4359User-agent: PerplexityBot
44- Disallow: /
45-
46- User-agent: Applebot-Extended
47- Disallow: /
48-
49- User-agent: ClaudeBot
50- Disallow: /
51-
52- User-agent: FacebookBot
60+ User-agent: PetalBot
61+ User-agent: PhindBot
62+ User-agent: Poseidon Research Crawler
63+ User-agent: QualifiedBot
64+ User-agent: QuillBot
65+ User-agent: quillbot .com
66+ User-agent: SBIntuitionsBot
67+ User-agent: Scrapy
68+ User-agent: SemrushBot
69+ User-agent: SemrushBot-BA
70+ User-agent: SemrushBot-CT
71+ User-agent: SemrushBot-OCOB
72+ User-agent: SemrushBot-SI
73+ User-agent: SemrushBot-SWA
74+ User-agent: Sidetrade indexer bot
75+ User-agent: TikTokSpider
76+ User-agent: Timpibot
77+ User-agent: VelenPublicWebCrawler
78+ User-agent: Webzio-Extended
79+ User-agent: wpbot
80+ User-agent: YandexAdditional
81+ User-agent: YandexAdditionalBot
82+ User-agent: YouBot
5383Disallow: /
0 commit comments