We've seen a lot of interest in long term memory and have spent a lot of time thinking about the best way to incorporate it into apps We've tried to distill some of these learnings into helper functions (and helper agents!) `pip install langmem` -> check it out
@hwchase17
-
TreeHacks Stanford: Building AI Agents Discussion
By
–
At treehacks on stanfords campus! Come say hi and talk about building agents
-
Closed Labs Restrict Top Models APIs, Open Source Becomes Critical
By
–
@SullyOmarr called it – closed labs will not release top models via apis for much longer Open source even more important to allow a developer ecosystem to flourish
-
Klarna’s AI Assistant Transforms Customer Support for 85 Million Users
By
–
How Klarna's AI assistant redefined customer support at scale for 85 million active users Customer support is one of the areas being disrupted most by GenAI, and Klarna has done this at scale Excited to partner with them on LangSmith/LangGraph! https://
blog.langchain.dev/customers-klar
na/
… -
Prebuilt AI Agents and Ecosystem Development Strategy
By
–
I hope there will be some prebuilt agents for those! We will likely not build them all but try to foster that ecosystem
-
LangChain Launch: New AI Integration Available Today
By
–
Excited to see this launch! Try it out in LangChain today
-
Multi-Agent System Architectures: Supervisor Patterns Released
By
–
There are many ways to build multi-agent systems – we just released a prebuilt package for one of the more common ones (supervisor/hierarchical) What common patterns/architectures should we do next?
-
Vizient Deploys GenAI Multi-Agent System Healthcare
By
–
Deploying GenAI is hard Deploying it in a reliable way in a regulated industry like healthcare is 10x harder Vizient chose to use LangGraph and LangSmith to power their multi-agent system Read more about how Vizient is empowering healthcare providers https://
blog.langchain.dev/customers-vizi
ent/
… -
Evaluating AI Agents: Key Questions and Expert Track
By
–
One of the biggest questions about agents is: "How do we evaluate them?" We will have a whole track on Evals at INTERRUPT I could't imagine a better speaker for that track than @sh_reya https://
interrupt.langchain.com -
Google Launches Gen AI Toolbox for Databases Public Beta
By
–
Announcing public beta of Gen AI Toolbox for Databases Excited to partner with Google on this launch! This is basically a "tool server" for database tools, making it easy for agents to call these tools Big thanks to Hamsa, Kurt, and the team! https://
cloud.google.com/blog/products/
ai-machine-learning/announcing-gen-ai-toolbox-for-databases-get-started-today?e=48754805
…