# agentsite-static-version=ff21e7fc-9649-4f65-9c07-4985f4dccf33 # keenable.ai > AI-optimized mirror of keenable.ai containing 12 pages totalling 16,649 words of clean markdown content, structured data, and semantic HTML. Original source: https://keenable.ai. Last updated: 2026-09-16T04:44:42.723Z. Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG). ## Homepage - [Keenable.ai — Independent Web Search API for AI](/content/site-root.html): Keenable is independent web search infrastructure for AI: our own crawler, index and ranking, and it gets better the more agents use it. (523 words) ## Articles & Blog Posts - [Terms of Service - Keenable.ai](/content/terms/index.html): These terms of service cover how you may use the Keenable search API, CLI, MCP server and website, including rules on acceptable use. (8,530 words) - [NEEDLE: The benchmark your search engine can't memorize - Keenable.ai](/content/blog/needle-the-benchmark-your-search-engine-can-t-memorize.html): Machines are now the majority of consumers of web content. AI agents will soon be the largest consumers of search. Agents need search because the information required to complete real tasks is often too fresh (”Who won the Dodgers game yesterday”) or too niche (”Can the same GM sensor be used across both 2007 and 2008 Silverado and Sierra platforms?”) to live in model weights or context. But search is not built for agents: every engine, including Keenable, falls short of what's achievable on agentic traffic. That gap is hard to measure, because overfitting and data leakage make standard search benchmarks like BrowseComp unreliable. To fix this, we introduce NEEDLE, a live, open-source benchmark for search engine quality. NEEDLE’s queries are drawn partly from real agent search logs and partly generated to reflect the search intents we observe in production. It runs continuously in public and anyone can reproduce it. All queries and metrics are on the live benchmark page, and the full evaluation code is in our GitHub repo. Contributions are welcome. (2,004 words) - [Natural conversation, live retrieval: Keenable search with Gradium - Keenable.ai](/content/blog/natural-conversation-live-retrieval-keenable-search-with-gradium.html): We’re partnering with Gradium to join realtime voice AI and web search. Gradbot, Gradium’s open source agent framework for fast, natural conversations, is adding support for Keenable search. Ask any voice agent something it has to look up, and you can hear the moment it happens: silence, while it searches. With Keenable under the hood, a Gradbot agent pulls answers from the live web as naturally as it speaks from memory. With Gradium’s voices, Keenable search experience now benefits from natural conversation and great voices. Hear it in the hosted demo: gradium.keenable.ai. (406 words) - [Accel-backed Keenable is indexing the web for AI agents - Keenable.ai](/content/blog/keenable-raised-26m-to-beat-google-in-the-agentic-search-market.html): Andrey Styskin, who previously led Russian search giant Yandex’s search, AI and cloud division, and German AI scientist Matthias Petri are working to solve that problem with their new startup, Keenable. The company recently came out of stealth $26 million in seed funding. Accel led the funding round, which also saw participation from Conviction Partners and some business angels. (84 words) - [Privacy Policy - Keenable.ai](/content/privacy/index.html): This privacy policy explains what Keenable collects through the search API and the console, how that data is used, and how to reach us. (2,527 words) - [SELECT the tail FROM the web - Keenable.ai](/content/blog/select-the-tail-from-the-web/index.html): Agents inherited the web search interface from humans: ten blue links with short snippets. That interface was designed for a person who will click one result and read it. An agent doing real work needs the full distribution of what the world has already tried, what worked, and what didn't. (1,906 words) - [Keenable Blog - Notes on Agent Search and Retrieval](/content/blog/index.html): Keenable blog covers agent search, retrieval quality and the integrations we ship, written by the engineers who build and run them. (68 words) - [Keenable now runs inside Lightpanda - Keenable.ai](/content/blog/keenable-now-runs-inside-lightpanda/index.html): Lightpanda Agent now searches with Keenable when no search key is configured. The integration shipped to main this week. (231 words) - [Keenable Pricing - Web Search API Cost per 1,000 Requests](/content/pricing/index.html): Keenable pricing starts with 100,000 free requests a month, then pay as you go per 1,000 requests, with volume rates for the AI labs. (61 words) ## About Pages - [What Is Keenable - Independent Web Search for AI](/content/about/index.html): Keenable is a research company building the largest independent web index, so AI models reach live web knowledge cheaply. Read what we build. (242 words) - [Contact Keenable - Talk to the Web Search API Team](/content/contact/index.html): Contact the Keenable team about search API access, volume rate limits, billing or an integration. Every message gets a human reply. (67 words) ## Resources - [Full Page Index](/index.html): Browse all cached pages with rich metadata - [About This Cache](/about.html): Methodology, technical details, and usage guidelines - [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery - [Robots.txt](/robots.txt): Crawler directives - [AgentSite Network](https://agentsite.network/network.html): Public index of AgentSites and their machine-readable resources