Ask your agent how many researchers Anthropic hired from other labs this year. You'll probably get a number and no idea where it came from. Keenable SELECT answers questions whose answer isn't printed on any page: it reads over a thousand pages in one run, keeps a row for everything it finds, and computes the answer from those rows. Every row keeps its source, so you can check where the answer came from. See what a finished research looks like, then run yours: app.keenable.ai/select/start

Keenable is now a web-fetch backend in @cognee_ Name what you need in the fetch call, and only that part of the page is chunked, embedded and left in the knowledge graph. Setup: keenable.ai/blog/keenable-is…

If you run Hermes, your agent has already been searching on Keenable. Last month traffic grew 8x, and we enabled 1M search requests a day from Hermes agents. Hermes agent’s ecosystem keeps growing, add your own key to lift the default limits: docs.keenable.ai/integration…

Keenable AI Open-Sources NEEDLE: A Live Search Benchmark That Rebuilds Its Query Set Every Hour Most search benchmarks are a fixed question set with a public answer key. That's not a benchmark for agents — because an agent with a fetch tool can just download the key mid-evaluation. Keenable open-sourced NEEDLE — a live search benchmark that rebuilds its query set instead of freezing one. News queries regenerate every hour from RSS feeds and Google Trends. Finance, scholar, and legal gold regenerates daily from public registries, SEC XBRL, arXiv, Europe PMC, CourtListener, and the eCFR. Rare-entity queries are sampled daily from public agent-trajectory logs. Here's what's actually interesting: → Queries are archived publicly after every run, so the defense isn't secrecy — it's that each run scores engines on queries newer than the models being tested → 18 engine configurations from 14 providers, one protocol: same query text, same 2,000-character evidence cap, one call at a time, judge blind to engine identity → Every score is read against ultimate, a pooled oracle engine that separates "this engine ranked badly" from "nobody found better." On rare-entity queries from real agent logs, the leader sits at 0.533 of that ceiling → There's an index-independence audit. Agreeing on good results proves nothing, so it flags a pair when they share a below-relevance URL, or share three-plus URLs on one query. In the published overlap data, Brave and You dot com are flagged on 89% of comparable queries Latency is treated as a quality metric — agents call search dozens of times per task, so p50 to p95 lands inside the user's wait. Full analysis: marktechpost.com/2026/08/31/… Technical Details: keenableai.github.io/needle/ @KeenableAI

AI agents will soon be the internet's biggest search users. But today's search engines aren't ready. We created an open-source live web search benchmark to track daily who is moving the NEEDLE for agents. Read more in our blog post:

Keenable is live. We’re excited to start telling our story: