diff --git a/data/bots/ai-robots-txt.yaml b/data/bots/ai-robots-txt.yaml
new file mode 100644
index 0000000..e515201
--- /dev/null
+++ b/data/bots/ai-robots-txt.yaml
@@ -0,0 +1,6 @@
+# Warning: Contains user agents that _must_ be blocked in robots.txt, or the opt-out will have no effect.
+# Note: Blocks human-directed/non-training user agents
+- name: "ai-robots-txt"
+  user_agent_regex: >-
+    AI2Bot|Ai2Bot-Dolma|aiHitBot|Amazonbot|anthropic-ai|Brightbot 1.0|Bytespider|CCBot|ChatGPT-User|Claude-SearchBot|Claude-User|Claude-Web|ClaudeBot|cohere-ai|cohere-training-data-crawler|Cotoyogi|Crawlspace|Diffbot|DuckAssistBot|FacebookBot|Factset_spyderbot|FirecrawlAgent|FriendlyCrawler|Google-CloudVertexBot|Google-Extended|GoogleOther|GoogleOther-Image|GoogleOther-Video|GPTBot|iaskspider/2.0|ICC-Crawler|ImagesiftBot|img2dataset|imgproxy|ISSCyberRiskCrawler|Kangaroo Bot|meta-externalagent|Meta-ExternalAgent|meta-externalfetcher|Meta-ExternalFetcher|MistralAI-User/1.0|NovaAct|OAI-SearchBot|omgili|omgilibot|Operator|PanguBot|Perplexity-User|PerplexityBot|PetalBot|QualifiedBot|Scrapy|SemrushBot-OCOB|SemrushBot-SWA|Sidetrade indexer bot|TikTokSpider|Timpibot|VelenPublicWebCrawler|Webzio-Extended|wpbot|YouBot
+  action: DENY