cloudflare-bot-directory 1.0.17 → 1.0.19

package/package.json

@@ -2,7 +2,7 @@
   "name": "cloudflare-bot-directory",
   "description": "CloudFlare Radar verified bots directory - 500+ web crawlers, search engine bots, and user agents as JSON for bot detection and traffic filtering",
   "homepage": "https://github.com/microlinkhq/cloudflare-bot-directory",
-  "version": "1.0.17",
+  "version": "1.0.19",
   "types": "./src/index.d.ts",
   "main": "./src/index.js",
   "exports": {

package/src/index.json

@@ -3,7 +3,7 @@
     "slug": "2checkout",
     "name": "2checkout",
     "kind": "BOT",
-    "operator": "2checkout",
+    "operator": "Verifone",
     "operatorUrl": "https://knowledgecenter.2checkout.com/API-Integration/Webhooks/",
     "category": "WEBHOOKS",
     "description": "2Checkout Payment Platform's webhooks integration for notifying websites about payment events. Now operated by Verifone.  ",
@@ -561,7 +561,7 @@
     "slug": "apify-website-content-crawler",
     "name": "Apify Website Content Crawler",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Apify",
     "operatorUrl": "https://apify.com/apify/website-content-crawler",
     "category": "AI_ASSISTANT",
     "description": "Crawl websites and extract content to feed AI apps. Convert web data to Markdown or HTML, download files, and more.",
@@ -658,7 +658,7 @@
     "slug": "atlassian-bot",
     "name": "atlassian-bot",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Atlassian",
     "operatorUrl": "https://support.atlassian.com/organization-administration/docs/connect-custom-website-to-rovo/",
     "category": "AI_CRAWLER",
     "description": "atlassian-bot is a crawler for custom 3P websites that indexes data for rovo search",
@@ -901,7 +901,7 @@
     "slug": "bigscootsmonitor",
     "name": "BigScootsMonitor",
     "kind": "BOT",
-    "operator": null,
+    "operator": "BigScoots",
     "operatorUrl": "https://monitor.bigscoots.dev",
     "category": "MONITORING_AND_ANALYTICS",
     "description": "BigScoots Managed Services Monitor - Uptime",
@@ -1095,7 +1095,7 @@
     "slug": "bluesky-app",
     "name": "Bluesky Link Preview Service",
     "kind": "BOT",
-    "operator": "Bluesky ",
+    "operator": "Bluesky",
     "operatorUrl": "https://blueskyweb.xyz/ ",
     "category": "PAGE_PREVIEW",
     "description": "Bluesky social pulls links in advance to render webpage previews.",
@@ -1192,7 +1192,7 @@
     "slug": "browserbase",
     "name": "Browserbase",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Browserbase",
     "operatorUrl": "https://browserbase.com",
     "category": "AI_ASSISTANT",
     "description": "Browserbase helps AI use the web. Autonomously reads, writes, and performs tasks on the web with a serverless browser.",
@@ -1204,7 +1204,7 @@
     "slug": "bufferlinkpreviewbot",
     "name": "Buffer Link Preview Bot",
     "kind": "BOT",
-    "operator": "buffer.com",
+    "operator": "Buffer",
     "operatorUrl": "https://scraper.buffer.com/about/bots/link-preview-bot",
     "category": "PAGE_PREVIEW",
     "description": "When Buffer users share links in their social media posts, their scraper helps create engaging previews.",
@@ -1318,7 +1318,7 @@
     "slug": "cartai-agentic-commerce-as-a-service",
     "name": "CartAI Agentic Commerce as a Service",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "CartAI",
     "operatorUrl": "https://docs.cartai.ai/docs/introduction",
     "category": "AI_ASSISTANT",
     "description": "CartAI B2B rails combine execution, payments, loyalty and affiliate networks to facilitate agentic commerce",
@@ -1489,7 +1489,7 @@
     "slug": "citibotsitecrawler",
     "name": "CitibotSiteCrawler",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Citibot",
     "operatorUrl": "https://www.citibot.io/",
     "category": "AI_CRAWLER",
     "description": "CitibotSiteCrawler collects public data from government websites to power Citibot’s AI civic engagement tools.",
@@ -2159,7 +2159,7 @@
     "slug": "daric2",
     "name": "Daric2",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Cloudflare",
     "operatorUrl": "https://developers.cloudflare.com/ai-crawl-control/",
     "category": "AI_CRAWLER",
     "description": "Cloudflare AI Crawl Control bot 2",
@@ -2171,7 +2171,7 @@
     "slug": "daric3",
     "name": "Daric3",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Cloudflare",
     "operatorUrl": "https://developers.cloudflare.com/ai-crawl-control/",
     "category": "AI_CRAWLER",
     "description": "Cloudflare AI Crawl Control bot 3",
@@ -2183,7 +2183,7 @@
     "slug": "daric4",
     "name": "Daric4",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Cloudflare",
     "operatorUrl": "https://developers.cloudflare.com/ai-crawl-control/",
     "category": "AI_CRAWLER",
     "description": "Cloudflare AI Crawl Control bot 4",
@@ -2389,7 +2389,7 @@
     "slug": "direqt-anomura",
     "name": "Direqt Anomura",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Direqt",
     "operatorUrl": "https://dashboarddocs.direqt.ai/direqt-bots/direqt-crawlers-and-user-agents",
     "category": "AI_SEARCH",
     "description": "Anomura is Direqt’s search crawler, it discovers and indexes pages their customers websites.",
@@ -2481,6 +2481,18 @@
       "Dratabot (+https://dratabot.com)"
     ]
   },
+  {
+    "slug": "drift-agent",
+    "name": "Drift Agent",
+    "kind": "AGENT",
+    "operator": "Drift Security",
+    "operatorUrl": "https://www.getdrift.ai",
+    "category": "AI_ASSISTANT",
+    "description": "The Drift Agent executes security and compliance tasks on behalf of the CISO office.",
+    "followsRobotsTxt": false,
+    "userAgentPatterns": [],
+    "userAgents": []
+  },
   {
     "slug": "drlinkcheck",
     "name": "Dr. Link Check",
@@ -2894,7 +2906,7 @@
     "slug": "fit-feeds-fetcher",
     "name": "FIT Feeds Fetcher",
     "kind": "BOT",
-    "operator": null,
+    "operator": "follow.it",
     "operatorUrl": "https://follow.it",
     "category": "FEED_FETCHER",
     "description": "This bot is used to fetch the RSS feed content of the websites owned by rightful publishers at follow.it",
@@ -2976,7 +2988,7 @@
     "slug": "freshping",
     "name": "Freshping",
     "kind": "BOT",
-    "operator": "freshping",
+    "operator": "Freshworks",
     "operatorUrl": "https://support.freshping.io/en/support/solutions/articles/50000003709-freshping-api-documentation",
     "category": "ACCESSIBILITY",
     "description": "Check website is online and issue an alert when its down",
@@ -3586,6 +3598,22 @@
       "Mozilla/5.0 (compatible; GuestpostsBot/2.0; +https://guestposts.com.br/blog/robot/)"
     ]
   },
+  {
+    "slug": "haiku-searchbot",
+    "name": "Haiku-SearchBot",
+    "kind": "AGENT",
+    "operator": "CLERK SAS",
+    "operatorUrl": "https://www.haiku.fr/robots-doc",
+    "category": "AI_ASSISTANT",
+    "description": "Haiku-SearchBot is for user actions in Haiku. When users ask Haiku a question, it may visit a web page to help answer.",
+    "followsRobotsTxt": false,
+    "userAgentPatterns": [
+      "Haiku-SearchBot"
+    ],
+    "userAgents": [
+      "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; Haiku-SearchBot/1.0; +https://haiku.fr/robots-doc"
+    ]
+  },
   {
     "slug": "hatena",
     "name": "Hatena",
@@ -3646,7 +3674,7 @@
     "slug": "henry-shopping-agent",
     "name": "Henry Shopping Agent",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Henry Labs",
     "operatorUrl": "https://docs.henrylabs.ai/",
     "category": "AI_ASSISTANT",
     "description": "Executes checkout via browser automation using a user's card and signed mandate",
@@ -3674,7 +3702,7 @@
     "slug": "hey-email-privacy-proxy-2",
     "name": "HEY Email Privacy Proxy",
     "kind": "BOT",
-    "operator": null,
+    "operator": "37signals",
     "operatorUrl": "https://www.hey.com/spy-trackers/",
     "category": "PAGE_PREVIEW",
     "description": "HEY email stops spy pixels and prevents user IP tracking by proxying all HTML email images, fonts, and external assets",
@@ -3754,7 +3782,7 @@
     "slug": "hubspot-crawler",
     "name": "HubSpot Crawler",
     "kind": "BOT",
-    "operator": "Hubspot",
+    "operator": "HubSpot",
     "operatorUrl": "http://www.hubspot.com/",
     "category": "OTHER",
     "description": "HubSpot offers a full platform of marketing, sales, customer service, and CRM software — plus the methodology, resources, and support — to help businesses grow better. Get started with free tools, and upgrade as you grow.",
@@ -4079,7 +4107,7 @@
     "slug": "jobswithgptcom-bot",
     "name": "jobswithgptcom-bot",
     "kind": "BOT",
-    "operator": "jobswithgptcom",
+    "operator": "JobsWithGPT",
     "operatorUrl": "https://jobswithgpt.com/bot.html",
     "category": "SEARCH_ENGINE_CRAWLER",
     "description": "Simple crawler focussing on only job postings for job search site.",
@@ -4127,7 +4155,7 @@
     "slug": "kakaotalk-scrap-2",
     "name": "KakaoTalk Scrap",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Kakao",
     "operatorUrl": "https://developers.kakao.com/docs/latest/en/message-template/common\\#scrap",
     "category": "PAGE_PREVIEW",
     "description": "The KakaoTalk scrap server collects and processes webpage data to create optimized previews for URLs.",
@@ -4175,7 +4203,7 @@
     "slug": "kernel",
     "name": "Kernel",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Kernel",
     "operatorUrl": "https://www.kernel.sh/docs",
     "category": "AI_ASSISTANT",
     "description": "Kernel is a browsers as a service platform that enables AI agents to browse the internet.",
@@ -4219,7 +4247,7 @@
     "slug": "klaviyoaibot",
     "name": "KlaviyoAIBot",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Klaviyo",
     "operatorUrl": "https://help.klaviyo.com/hc/en-us/articles/40496146232219",
     "category": "AI_SEARCH",
     "description": "Klaviyo’s web crawler for its Kai Customer Agent feature.",
@@ -4693,7 +4721,7 @@
     "slug": "melonmesabot",
     "name": "MelonMesa Bot",
     "kind": "BOT",
-    "operator": null,
+    "operator": "MelonMesa",
     "operatorUrl": "https://centcom.melonmesa.com/",
     "category": "OTHER",
     "description": "This bot is used to aggregate data about a popular online multiplayer game from consenting hosts who have opted-in to this collection. The data that is aggregated is reflected in a panel where players can freely search through the aggregated data. Any modification or deletion of data from the sources (consenting hosts) is reflected within the application's database within 30 minutes. The application scrapes each host for new data every five minutes, with a more thorough check for modified data every 30 minutes.",
@@ -5100,7 +5128,7 @@
     "slug": "nava-labs-asp-dev",
     "name": "Nava Labs ASP (Dev)",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Nava Labs",
     "operatorUrl": "https://dev.labs-asp.navateam.com/bot-disclosure",
     "category": "AI_ASSISTANT",
     "description": "Bot to assist social workers in navigating safety net benefit websites.",
@@ -5149,7 +5177,7 @@
     "slug": "nekuda-payment-executor",
     "name": "Nekuda Payment Executor",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Nekuda",
     "operatorUrl": "https://docs.nekuda.ai/payment-executor",
     "category": "AI_ASSISTANT",
     "description": "Executes secure checkout via browser agent using user card and signed mandate.",
@@ -5388,7 +5416,7 @@
     "slug": "nostra",
     "name": "Nostra",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Nostra",
     "operatorUrl": "https://www.nostra.ai/edge-optimization",
     "category": "SEARCH_ENGINE_OPTIMIZATION",
     "description": "Nostra accelerates site speed for managed web platforms",
@@ -5445,6 +5473,22 @@
       "OhDear.app (+https://ohdear.app/docs/checks/uptime)"
     ]
   },
+  {
+    "slug": "okx-dolphin-crawler",
+    "name": "OKX-dolphin-crawler",
+    "kind": "BOT",
+    "operator": "OKX",
+    "operatorUrl": "https://web3.okx.com/security/crawler-allowlist",
+    "category": "SECURITY",
+    "description": "OKX Dolphin Crawler simulates visits to target web pages as part of malicious dApp scanning",
+    "followsRobotsTxt": false,
+    "userAgentPatterns": [
+      "OKX-dolphin-crawler"
+    ],
+    "userAgents": [
+      "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 OKX-dolphin-crawler"
+    ]
+  },
   {
     "slug": "omnisend",
     "name": "Omnisend",
@@ -5642,7 +5686,7 @@
     "slug": "paddle-webhooks",
     "name": "Paddle Webhooks",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Paddle",
     "operatorUrl": "https://developer.paddle.com/webhooks/overview",
     "category": "WEBHOOKS",
     "description": "Webhooks let you get notified when events happen in Paddle.",
@@ -5974,7 +6018,7 @@
     "slug": "productsup-crawler",
     "name": "Productsup Crawler",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Productsup",
     "operatorUrl": "https://help.productsup.com/en/29437-29446-import-data-by-crawling-your-website.html",
     "category": "ADVERTISING_AND_MARKETING",
     "description": "Productsup crawls websites to import additional product data.",
@@ -6136,7 +6180,7 @@
     "slug": "quartr-crawler",
     "name": "Quartr Crawler",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Quartr",
     "operatorUrl": "https://quartr.com",
     "category": "AGGREGATOR",
     "description": "Quartr uses a crawler to obtain and deliver investor relations material",
@@ -6233,7 +6277,7 @@
     "slug": "recurly",
     "name": "Recurly Webhooks",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Recurly",
     "operatorUrl": "https://recurly.com/",
     "category": "WEBHOOKS",
     "description": "We send webhooks to our customers to inform them of events occurring on own platform relevant to their site",
@@ -6341,6 +6385,23 @@
       "Mozilla/5.0 (X11; Linux x86_64; Rigor) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.75 Safari/537.36"
     ]
   },
+  {
+    "slug": "robinbot",
+    "name": "Robinbot",
+    "kind": "AGENT",
+    "operator": "Robin Education",
+    "operatorUrl": "https://www.robin.education",
+    "category": "MONITORING_AND_ANALYTICS",
+    "description": "Robin automatically scans school websites in the UK, providing compliance checks against statutory requirements.",
+    "followsRobotsTxt": false,
+    "userAgentPatterns": [
+      "Robinbot"
+    ],
+    "userAgents": [
+      "Robinbot/1.0",
+      "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; Robinbot/1.0; +https://www.robin.education) Chrome/131.0.0.0 Safari/537.36"
+    ]
+  },
   {
     "slug": "rogerbot",
     "name": "Moz rogerbot",
@@ -6393,7 +6454,7 @@
     "slug": "ryebot",
     "name": "RyeBot",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Rye",
     "operatorUrl": "https://docs.rye.com/api-v2-experimental/ryebot",
     "category": "AI_ASSISTANT",
     "description": "Agentic checkout assistant that purchases products on behalf of end users with their explicit consent.",
@@ -6535,7 +6596,7 @@
     "slug": "semrush-ba",
     "name": "SemrushBotBacklinkAudit",
     "kind": "BOT",
-    "operator": "SEMrush",
+    "operator": "Semrush",
     "operatorUrl": "https://www.semrush.com/backlink_audit/",
     "category": "SEARCH_ENGINE_OPTIMIZATION",
     "description": "Data collected by SEMrushBot is used for the Backlink Audit tool to check website backlinks",
@@ -6567,7 +6628,7 @@
     "slug": "semrush-lb",
     "name": "SemrushBotLinkBuilding",
     "kind": "BOT",
-    "operator": "SEMrush",
+    "operator": "Semrush",
     "operatorUrl": "https://www.semrush.com/link_building/",
     "category": "SEARCH_ENGINE_OPTIMIZATION",
     "description": "Data collected by SEMrushBot is used for the Link Building tool to check website backlinks",
@@ -6632,7 +6693,7 @@
     "slug": "semrush-swa",
     "name": "SemrushBotSwa",
     "kind": "BOT",
-    "operator": "SEMrush",
+    "operator": "Semrush",
     "operatorUrl": "https://www.semrush.com/swa/",
     "category": "AI_CRAWLER",
     "description": "Data collected by SEMrushBot is used for the SEO Writing Assistant tool to check if URL is accessible",
@@ -6974,7 +7035,7 @@
     "slug": "siteimprove-linkcheck",
     "name": "LinkCheck",
     "kind": "BOT",
-    "operator": "SiteImprove",
+    "operator": "Siteimprove",
     "operatorUrl": "https://support.siteimprove.com/hc/en-gb/articles/115000402352-Siteimprove-s-Crawler-Frequently-Asked-Questions",
     "category": "SEARCH_ENGINE_OPTIMIZATION",
     "description": "The Siteimprove LinkCheck crawler analyzes and monitors websites for quality assurance, SEO, and accessibility purposes, and keeps website content in line with brand guidelines and organizational policies.",
@@ -7118,7 +7179,7 @@
     "slug": "smarsh",
     "name": "SmarshBot",
     "kind": "BOT",
-    "operator": "https://central.smarsh.com/s/",
+    "operator": "Smarsh",
     "operatorUrl": "https://www.smarsh.com/platform/compliance-management/web-archive",
     "category": "SECURITY",
     "description": "Providing archiving solutions to clients for compliance purposes",
@@ -7198,7 +7259,7 @@
     "slug": "sora-caisse-pos",
     "name": "Sora Caisse POS",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Sora Caisse POS",
     "operatorUrl": "https://www.sora-caisse.com/sora.pdf",
     "category": "OTHER",
     "description": "POS software connected to prestashop ecommerce website",
@@ -7555,7 +7616,7 @@
     "slug": "terracotta",
     "name": "Terracotta",
     "kind": "BOT",
-    "operator": null,
+    "operator": "Ceramic",
     "operatorUrl": "https://github.com/CeramicTeam/CeramicTerracotta",
     "category": "SEARCH_ENGINE_CRAWLER",
     "description": "The Terracotta bot scrapes websites for use in generating indices for serving searches using Ceramic's search product.",
@@ -7877,7 +7938,7 @@
     "slug": "visually-io-shopify-editor",
     "name": "Visually.io Shopify Editor",
     "kind": "AGENT",
-    "operator": null,
+    "operator": "Visually.io",
     "operatorUrl": "https://help.visually.io/visually.io-editor-cloudflare-signed-agent",
     "category": "AI_ASSISTANT",
     "description": "Shopify theme editor alternative for live, real-time store editing via a secure iframe and controlled proxy.",
@@ -7889,7 +7950,7 @@
     "slug": "w3-validator-services",
     "name": "W3 Validator Services",
     "kind": "BOT",
-    "operator": "World Wide Web Consortium (W3C) ",
+    "operator": "World Wide Web Consortium (W3C)",
     "operatorUrl": "https://validator.w3.org/services",
     "category": "SEARCH_ENGINE_OPTIMIZATION",
     "description": " W3C provides various free validation services that help check the conformance of Web sites against open standards. ",
@@ -8114,7 +8175,7 @@
     "slug": "wordpress-namecheap",
     "name": "Wordpress Namecheap",
     "kind": "BOT",
-    "operator": "namecheap",
+    "operator": "Namecheap",
     "operatorUrl": "namecheap.com",
     "category": "OTHER",
     "description": "This is the major egress IP for our containerised WordPress platform so it is likely to be many flavours of WordPress and the potential to be any domain.",
@@ -8501,7 +8562,7 @@
     "slug": "youbot",
     "name": "YouBot",
     "kind": "BOT",
-    "operator": null,
+    "operator": "You.com",
     "operatorUrl": "https://docs.you.com/youbot",
     "category": "SEARCH_ENGINE_CRAWLER",
     "description": "You.com Search Engine Crawler",
@@ -8545,6 +8606,22 @@
       "Zendesk Webhook"
     ]
   },
+  {
+    "slug": "zipchatbot",
+    "name": "ZipchatBot",
+    "kind": "AGENT",
+    "operator": "Zipchat Inc",
+    "operatorUrl": "https://www.zipchat.ai/bot",
+    "category": "AI_ASSISTANT",
+    "description": "AI assistant for e-commerce stores. Only crawls sites upon request from the site owner.",
+    "followsRobotsTxt": false,
+    "userAgentPatterns": [
+      "ZipchatBot"
+    ],
+    "userAgents": [
+      "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko) compatible; ZipchatBot/1.0; +https://zipchat.ai/bot"
+    ]
+  },
   {
     "slug": "zoominfobot",
     "name": "ZoomInfo",
@@ -8581,7 +8658,7 @@
     "slug": "zvelo-bot",
     "name": "Zvelo",
     "kind": "BOT",
-    "operator": null,
+    "operator": "zvelo",
     "operatorUrl": "https://zvelo.com",
     "category": "MONITORING_AND_ANALYTICS",
     "description": "zvelo fetches content for web categorization.",