If you’re looking to use pydantic with langgraph – some big performance improvements just landed
@hwchase17
-

Web-Based MCP Clients Enable Broader Adoption
By
–
Need to dig in more but this is great!!!! Will enable web-based clients for MCP (which should help it take off even more IMO)
-

Evaluating and Scaling AI Agents: Deployment and Iteration
By
–
Evaluating and Scaling AI Agents Building an agent in just the start. After a prototype, you need to make sure it actually works, deploy it, and then iterate on it based on feedback We'll be chatting about this on Thursday! Come join us in SF https://
lu.ma/x7ohaj2c -
LangGraph JS Memory Management Updates
By
–
we've been a bunch around memory in langgraph JS… check it out
-

2025: The Year Agents Move From Hype to Production
By
–
people are saying 2025 is the year of agents… agents have been here for the past year. building agents requires new tools and a new mental model Replit, LinkedIn, Uber, Elastic are using LangGraph/LangSmith to help power their agents https://
blog.langchain.dev/top-5-langgrap
h-agents-in-production-2024/
… -
Fastest Way to Get Started with JavaScript Agents
By
–
fastest way to get started with agents in javascript🚤
— Harrison Chase (@hwchase17) 15 mars 2025
prebuilt templates, UI, helpful installer… it's got it all! https://t.co/2NMNddrHqNfastest way to get started with agents in javascript prebuilt templates, UI, helpful installer… it's got it all!
-

Speeding up AI agents: latency reduction techniques
By
–
How do I speed up my agent? I get asked this question a bunch, so I wrote a quick blog on it. Techniques we see getting used: – Identifying where the latency is coming from
– Changing the UX to reduce the “perceived” latency
– Making fewer LLM calls
– Speeding up LLM calls
– -
Can AI agents reliably build their own tools autonomously
By
–
imo this is too researchy. agents are tough enough to get working with static tools. you really trust them to build their own?
-

Multi-Agent Example with Local Models by RLanceMartin
By
–
Great stuff from @RLanceMartin getting a multi agent example with local models
