# GeekVault is an API catalog built for AI agents to discover and use it — # we explicitly allow every crawler/agent we could find (community list via # ai.robots.txt + Cloudflare's AI bot reference), instead of blocking them # like a content site protecting its IP would. User-agent: * Allow: / User-agent: AddSearchBot Allow: / User-agent: AgentDataBot Allow: / User-agent: AgentTimes Allow: / User-agent: AI2Bot Allow: / User-agent: AI2Bot-DeepResearchEval Allow: / User-agent: Ai2Bot-Dolma Allow: / User-agent: aiHitBot Allow: / User-agent: AIWebIndex Allow: / User-agent: amazon-kendra Allow: / User-agent: amazon-QBusiness Allow: / User-agent: Amazonbot Allow: / User-agent: AmazonBuyForMe Allow: / User-agent: Amzn-SearchBot Allow: / User-agent: Amzn-User Allow: / User-agent: Andibot Allow: / User-agent: Anomura Allow: / User-agent: anthropic-ai Allow: / User-agent: ApifyBot Allow: / User-agent: ApifyWebsiteContentCrawler Allow: / User-agent: Applebot Allow: / User-agent: Applebot-Extended Allow: / User-agent: Aranet-SearchBot Allow: / User-agent: atlassian-bot Allow: / User-agent: Awario Allow: / User-agent: AzureAI-SearchBot Allow: / User-agent: bedrockbot Allow: / User-agent: bigsur.ai Allow: / User-agent: BixelBot Allow: / User-agent: Bravebot Allow: / User-agent: Brightbot Allow: / User-agent: Brightbot 1.0 Allow: / User-agent: BuddyBot Allow: / User-agent: Bytespider Allow: / User-agent: CCBot Allow: / User-agent: Channel3Bot Allow: / User-agent: ChatGLM-Spider Allow: / User-agent: ChatGPT Agent Allow: / User-agent: ChatGPT-User Allow: / User-agent: Claude-Code Allow: / User-agent: Claude-SearchBot Allow: / User-agent: Claude-User Allow: / User-agent: Claude-Web Allow: / User-agent: ClaudeBot Allow: / User-agent: Cloudflare-AutoRAG Allow: / User-agent: CloudflareBrowserRenderingCrawler Allow: / User-agent: CloudVertexBot Allow: / User-agent: cohere-ai Allow: / User-agent: cohere-training-data-crawler Allow: / User-agent: Cotoyogi Allow: / User-agent: CragCrawler Allow: / User-agent: Crawl4AI Allow: / User-agent: Crawlspace Allow: / User-agent: Cursor Allow: / User-agent: Datenbank Crawler Allow: / User-agent: DeepSeekBot Allow: / User-agent: Devin Allow: / User-agent: Diffbot Allow: / User-agent: Diffbot-User Allow: / User-agent: DoubaoBot Allow: / User-agent: DuckAssistBot Allow: / User-agent: Echobot Bot Allow: / User-agent: EchoboxBot Allow: / User-agent: ERNIEBot Allow: / User-agent: ExaBot Allow: / User-agent: ExaSearchBot Allow: / User-agent: FacebookBot Allow: / User-agent: facebookexternalhit Allow: / User-agent: Factset_spyderbot Allow: / User-agent: FirecrawlAgent Allow: / User-agent: FriendlyCrawler Allow: / User-agent: GeistHaus-PageFetcher Allow: / User-agent: Gemini-Deep-Research Allow: / User-agent: Google-Agent Allow: / User-agent: Google-CloudVertexBot Allow: / User-agent: Google-Extended Allow: / User-agent: Google-Firebase Allow: / User-agent: Google-Gemini-CLI Allow: / User-agent: Google-NotebookLM Allow: / User-agent: GoogleAgent-Mariner Allow: / User-agent: GoogleAgent-URLContext Allow: / User-agent: GoogleOther Allow: / User-agent: GoogleOther-Image Allow: / User-agent: GoogleOther-Video Allow: / User-agent: GPTBot Allow: / User-agent: GrokAppAndroid Allow: / User-agent: GrokBot Allow: / User-agent: HenkBot Allow: / User-agent: Hunyuan Allow: / User-agent: iAskBot Allow: / User-agent: iaskspider Allow: / User-agent: iaskspider/2.0 Allow: / User-agent: ICC-Crawler Allow: / User-agent: ImagesiftBot Allow: / User-agent: imageSpider Allow: / User-agent: img2dataset Allow: / User-agent: ISSCyberRiskCrawler Allow: / User-agent: kagi-fetcher Allow: / User-agent: Kangaroo Bot Allow: / User-agent: KeenableBot Allow: / User-agent: Kimi-Agent Allow: / User-agent: Kimi-SearchBot Allow: / User-agent: Kimi-User Allow: / User-agent: KimiBot Allow: / User-agent: KlaviyoAIBot Allow: / User-agent: KunatoCrawler Allow: / User-agent: laion-huggingface-processor Allow: / User-agent: LAIONDownloader Allow: / User-agent: LCC Allow: / User-agent: Lightpanda Allow: / User-agent: LinerBot Allow: / User-agent: Linguee Bot Allow: / User-agent: LinkupBot Allow: / User-agent: Manus-User Allow: / User-agent: meta-externalagent Allow: / User-agent: Meta-ExternalAgent Allow: / User-agent: meta-externalfetcher Allow: / User-agent: Meta-ExternalFetcher Allow: / User-agent: meta-webindexer Allow: / User-agent: MistralAI-Index Allow: / User-agent: MistralAI-Training Allow: / User-agent: MistralAI-User Allow: / User-agent: MistralAI-User/1.0 Allow: / User-agent: MoonshotBot Allow: / User-agent: Mozilla-Tabstack Allow: / User-agent: MyCentralAIScraperBot Allow: / User-agent: NagetBot Allow: / User-agent: nbot Allow: / User-agent: netEstate Imprint Crawler Allow: / User-agent: newsai Allow: / User-agent: NotebookLM Allow: / User-agent: NovaAct Allow: / User-agent: OAI-AdsBot Allow: / User-agent: OAI-SearchBot Allow: / User-agent: omgili Allow: / User-agent: omgilibot Allow: / User-agent: OpenAI Allow: / User-agent: opencode Allow: / User-agent: Operator Allow: / User-agent: PanguBot Allow: / User-agent: Panscient Allow: / User-agent: panscient.com Allow: / User-agent: Perplexity-User Allow: / User-agent: PerplexityBot Allow: / User-agent: PetalBot Allow: / User-agent: PhindBot Allow: / User-agent: Poggio-Citations Allow: / User-agent: Poseidon Research Crawler Allow: / User-agent: qodercli Allow: / User-agent: QualifiedBot Allow: / User-agent: Querit-SearchBot Allow: / User-agent: QueritBot Allow: / User-agent: QuillBot Allow: / User-agent: quillbot.com Allow: / User-agent: QwenBot Allow: / User-agent: Reflectionbot Allow: / User-agent: SBIntuitionsBot Allow: / User-agent: Scrapy Allow: / User-agent: SemrushBot-OCOB Allow: / User-agent: SemrushBot-SWA Allow: / User-agent: Shap-User Allow: / User-agent: ShapBot Allow: / User-agent: Sidetrade indexer bot Allow: / User-agent: Spider Allow: / User-agent: TavilyBot Allow: / User-agent: Terra Cotta Allow: / User-agent: TerraCotta Allow: / User-agent: Thinkbot Allow: / User-agent: TikTokSpider Allow: / User-agent: Timpibot Allow: / User-agent: TongyiBot Allow: / User-agent: Trae Allow: / User-agent: TwinAgent Allow: / User-agent: UseAI Allow: / User-agent: VelenPublicWebCrawler Allow: / User-agent: WARDBot Allow: / User-agent: Webzio-Extended Allow: / User-agent: webzio-extended Allow: / User-agent: wpbot Allow: / User-agent: WRTNBot Allow: / User-agent: xAI-Grok Allow: / User-agent: YaK Allow: / User-agent: YandexAdditional Allow: / User-agent: YandexAdditionalBot Allow: / User-agent: YiBot Allow: / User-agent: YiyanBot Allow: / User-agent: YouBot Allow: / User-agent: ZanistaBot Allow: / User-agent: Googlebot Allow: / User-agent: bingbot Allow: / User-agent: YandexBot Allow: / User-agent: Yandex Allow: / User-agent: Mail.RU_Bot Allow: / User-agent: Sogou web spider Allow: / User-agent: 360Spider Allow: / User-agent: Rambler Allow: / User-agent: Naver Yeti Allow: / User-agent: DeepSeek Allow: / User-agent: Sensetime Allow: / User-agent: SparkDesk Allow: / # Agent/LLM manifest (llms.txt format) # https://geekvault.dev/llms.txt # Machine-readable x402 payment catalog # https://api.geekvault.dev/.well-known/x402 Sitemap: https://geekvault.dev/sitemap.xml