I'm throwing the AI meetup I wish existed Production grade AI Memory * Sam Whitmore - Social memory New Computer * Nicole Hedley - Memory for clients @ Headstart * Will Fu-Hinthorn - Memory types LangChain * eric zakariasson - $9B memetic agents Cursor SF come join

An open source quick start to build your own version of “deep research”, powered by the Gemini API! github.com/google-gemini/…

Great work by Philipp Schmid and the team on this!

I’m speaking at the LangChain London meetup tomorrow organized by the awesome chaeyoona 🎉 The meetup was sold out pretty much on the same day it was published♥️ Excited to have more in the future🥳

Today,Microsoft is excited to announce our partnership with LangChain. Together, we're making AI safer and more accessible for enterprises. Microsoft cares about open source and we're working to make AI apps built with LangChain secure to run on Azure. Learn more:

We're excited to announce our partnership with @langchain. Together, we're making AI safer and more accessible for open source and enterprises. Learn more: msft.it/6017SWeWh

🧘 Developer Experience improvements for LangGraph.js Finally, we've made a bunch of changes to improve the day-to-day developer experience with LangGraph 0.3! Here are some of the highlights: 🧵

📊Benchmarking Multi-Agent Architectures As more systems become multi-agent, this begs the question: how do you best orchestrate across multiple agents? We did some initial benchmarking, including some improvements to our supervisor approach Blog: blog.langchain.dev/benchmarking-m…

> be Sam Whitmore > physics labs at harvard & cambridge > self-teach code w/ tensor equations > join kensho as early engineer. ship data pipelines for wall st. > promoted to head of eng > guide team through $550M acquisition > forbes30u30finance.jpg > co-found new computer with

Good post. I still think multi-agent mainly useful if it’s required by actual logical constraints, which is seldom the case . And if you do build it, getting context sharing between agents is key

Which app will be the first to show ads while the model thinks?

lu.ma/krkqwl5x

Super excited to connect with LangChain developers at GIAC! Had the pleasure of presenting "ALL in AI Agent," showcasing the incredible synergy of LangGraph + LangChain + LangSmith. If you’re already part of the journey, don’t miss out the LangGraph Platform, give it a try!

Investment research, accelerated. Morningstar, Inc. built Mo, their AI research assistant, using LangGraph — helping users cut through massive datasets to surface precise, verifiable investment insights. Aisis Julian (Senior Software Engineer) and her team at Morningstar have

.Sam Whitmore crushing it at AI Memory She is stepping through the evolution of memory she’s built at New Computer Recording coming soon - absolutely gold

this was so much fun! thanks for organizing, Greg Kamradt !! excited to share recording soon :)

really enjoyed the talks from WFH Sam Whitmore Yash Gaitonde and Nicole Hedley - thanks for organizing it Greg Kamradt and LangChain! here's 3 things i found very useful from what they had to share 🧵

At OpenPipe we built an entire SFT platform before pivoting to RL. It's theoretically possible to get similar results with either approach. So why change? Compared to SFT, RL gets you: - Far better generalization from small datasets. With just 16 training examples you can get