Tavily

luma.com/fpxsdfhl <- Berlin

Did you miss our Builders and Brews event in San Francisco? Well we’ve got good news. We’re going to be in London May 22nd with Nebius and Zapier, and Berlin May 27th with Nebius and n8n. Register for your spot today. luma.com/1rna5bdp

Day two of @LangChain Interrupt is happening now! Stop by booth 4 to chat about what you're building and maybe check out the swag situation.

Can't wait for Agents After Dark! There are still some spots open if people want to sign up. luma.com/paxjj7qo

We’re back at LangChain Interrupt as a sponsor for year two and things kick off today: ❓ AMA with @EvanRimer from Tavily and Sujee Maniyam at 3:50 PM 💻 Live demos of Tavily Deep Research + a competitive intelligence agent built with LangChain Fleet, Tavily Search, and Nebius inference 🎁 Swag, giveaways, and a few surprises If you’re around, come hang with the Tavily team at booth 4, let us know what you’ve been building, and follow along here on X for updates throughout the event.

You're not going to want to miss this event.

What’s special about the @LangChain community is that it’s built by those who are willing to take the extra step to push the boundaries of what’s possible. It’s a community that builds technologies that are not gated by one company, fueled with enthusiasm and creativity. Super excited to join again this year - let’s see how much this community has grown 🚀 @hwchase17 @tavilyai

Hermes Agent is a glimpse into where agents are heading. It learns from every session, writes its own skills, and builds memory over time. That makes search quality way more important. If bad data gets pulled in once it sticks around and compounds. Tavily FDE @lakshyaag put together a quick breakdown of how Tavily plugs into Hermes to improve search, extraction, and real-time research for these long-running agents. If you’re building anything with persistent memory, this is worth a read. tavily.com/blog/hermes-ag…

If you're a fan of Tavily integrations you'll want to check out our latest newsletter! linkedin.com/pulse/agents-d…

April was a busy one for Tavily. We rolled out new integrations across the agent ecosystem and partnered with teams like JetBrains (Junie) and Snowflake to build real production-ready tools. On top of that, we spent time with builders at HumanX, ICLR, AI Dev Day, and we’re heading to LangChain Interrupt next. We pulled everything together here tavily.com/blog/whats-new…

We’re now live on @mastra with a native Tavily integration with doc updates, as well as on mastracode with new Tavily native imports. Now instead of manually stitching APIs together, your agent can call Tavily search, filter results, and extract structured data just like any other built-in tool. mastra.ai/reference/tool…

Closed sandboxes aren’t the future. Portable skills + real-time retrieval are. Tavily enables both without locking you into one model or API. Tavily.com

Tavily is now integrated into @TryArcade , which will enable secure, production-ready workflows. From financial research and CRM enrichment to healthcare, legal, and market intelligence, teams can automate complex, multi-step workflows with real-time data, secure execution, and fully auditable actions. Check out a full rundown here: tavily.com/blog/tavily-is…

The first Agent Readiness Report is out from Ora, and what does it reveal? 99% of the internet isn't usable by agents. At Tavily we've known for a long time that reliable access to up-to-date data is the difference between production-ready and wild hallucination. ora.run/blog/state-of-…

Tavily MCP is now available in the @Copilot Studio. Ready to bring Search, Extract, Crawl, Map and Research to your Logic and Power Apps, as well as your Power Automate workflows? Head over to learn.microsoft.com/en-us/connecto… for directions on getting up and running.

We’ve been hosting and co-hosting events with incredible partners, community builders, and universities around the world. Does that sound like something you want to get involved with? Check out where we’re heading next! 👇 Coming up… 🗽 NYU Hackathon: New York (April 23) 🗽 Elastic Developer Meetup: New York (April 23) 🐻 HackEurope: Berlin (April 25–26) 🗽 HackNation (Worldwide): New York (April 25–26) 🌉 Builders & Brews: San Francisco (April 27) 🐻 Nebius AI Builder Day: Berlin (April 28) 🌉 Elastic Meetup: San Francisco (April 28) 🌉 OpenAI Hackathon w/ AGI House: San Francisco (May 9) 🇬🇧 Nebius AI Builder Day: London (May 21) 🇬🇧 Builders & Brews: London (May 22) 🐻 Builders & Brews: Berlin (May 27) See all our events at luma.com/eventstavily

Dynamic filtering + real-time search = 🔥 Tavily lets agents both: fetch fresh info AND filter it before context tavily.com/blog/dynamic-f…

Recently @jetbrains shipped their coding agent, Junie, and integrated Tavily to ground responses with real-time web search. "Before web search, the model would hallucinate library methods it didn't know. I ran into this myself building a Telegram integration; it was confidently wrong. Grounding it with real-time web search fixed that immediately." - Nick Frolov Head of Product at Junie. Paired with high-quality, pre-extracted retrieval and citations from Tavily, Junie keeps context clean and outputs verifiable so developers stay in flow and spend less time debugging hallucinated code. You can read all about it in our latest case study here: tavily.com/blog/jetbrains…

RAG is cool. Wrong answers are not. Tavily = real-time sanity check for your AI 🤝