Each agent will need its own search API key to get personalized results. Excited to work with @agentmail on this. Two agents search “Andrey Styskin biography”. HR wants artifacts: projects I’ve built, articles I’ve written. Sales wants common ground: past companies, communities, shared connections. With separate IDs, @KeenableAI will learn from the results each agent looks and personalize retrieval and ranking. We’re building the whole search stack to connect each agent with the knowledge it actually needs.

Introducing Keenable Dynamic Snippets Now your agent can spend 50% fewer tokens on search tasks and look deeper into documents. Enabled for everyone. Read our technical report to see how we built Dynamic Snippets while preserving our 200ms p95 search latency: keenable.ai/blog/keenable-sn…

We keep building the fastest way to find information in Internet. Now 2x more token efficient for your agents. Read our tech report how we built it and what the impact is on agentic benchmarks.

Your Named Agents can sign up for Keenable and get the web search infrastructure they actually need

If you also don't remember the exact title of the tutorials, you can find them with Keenable in your Claude

Love seeing more work on better search evals for agents. @ValsAI uses private, expert-written tasks. With NEEDLE, we took a different approach: fresh queries every run, with the fully public benchmark.

When agents retrieve information from the web, they can often read it directly from HTML. But most of the valuable sites render content dynamically. More than 35% of our answers depend on them. Rendering these pages is up to 400x more expensive than reading static HTML. Lightpanda makes this scalable: 4× faster and 6× more cost-efficient than Chromium.

We are looking for a founding GTM hire to join the Keenable team. Remote: US, Bay Area preferred. The job sits between the engineering team and our customers, so you will: - talk to the researchers and ML engineers who evaluate web search at AI labs and inference platforms, - build the demo inside their own agent or eval harness and show the result on their queries, not ours, - run evals and pilots to a verdict, closing the deal yourself when the terms are standard, and - own integrations with inference platforms and agent frameworks, and the funnel that turns their usage into accounts. In August we came out of stealth with $26M led by Accel, with Conviction. We have an independent index of more than 100 billion documents, purpose-built for AI agents. Now we’re growing the team behind it. Know the right person? Send them the link: app.keenable.ai/careers/foun…

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…