I get this question a bunch. Developers generally first spend time getting the agent to work, but then they turn their attention to speed and cost. There are few things we see developers doing:

• Identifying where the latency is coming from
• Changing the UX to reduce the “perceived”

Model Context Protocol (MCP) is creating quite the stir on Twitter – but is it actually useful, or just noise? In this back and forth, Harrison Chase (LangChain CEO) and Nuno Campos (LangGraph Lead) debate whether MCP lives up to the hype.

Harrison: I’ll take the position that

Editor's note: This is a guest blog post from our friends at Build.inc. They built one of the more complex multi-agent workflows we've seen - with over 25 sub agents. Check out the screenshot of their graph for an idea of the complexity. They also

By Nuno Campos and Vadym Barda

Over the past year, we’ve invested heavily in making LangGraph the go-to framework for building AI agents. With companies like Replit, Klarna, LinkedIn and Uber choosing to build on top of LangGraph, we have more conviction than ever that we are on

Evaluations (evals) are important for bringing reliable LLM powered applications or agents to production, but it can be hard to know where to start when building evaluations from scratch. Our new packages—openevals and agentevals—provide a set of evaluators and a common framework that you can easily

Editor's note: this is a guest post from our friends at Onyx. As LangGraph has matured, we've seen more and more companies (Klarna, Replit, AppFolio, etc) start to use it as their agent framework of choice. We thought this was a great blog describing in detail

Today we're releasing the LangMem SDK, a library that helps your agents learn and improve through long-term memory.

It provides tooling to extract information from conversations, optimize agent behavior through prompt updates, and maintain long-term memory about behaviors, facts, and events.

You can use its core API with