Building LangGraph: Designing an Agent Runtime from first principles
In this blog piece, you’ll learn why and how we built LangGraph for production agents—focusing on control, durability, and the core features needed to scale.
GitHub - bytedance/deer-flow: DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source communit...
Understanding multi-agent handoffs
Handoffs are a central concept in multi-agent systems.
LangGraph swarm is built on them.
But, they can be hard to understand.
Here, we break-down the swarm handoff mechanism.
📽️:
https://t.co/YkSCFeg9A8
Counting tokens is a useful task in natural language processing (NLP) that allows us to measure the length and complexity of a text. The two important use cases for counting the tokens are: controlling the length of the prompt - models has limit …
LangGraph is a multi-agent framework. This means not only interacting with other LangGraph agents, but all other types of agents as well, regardless of how they are built. Today we are taking a few steps to to build towards this vision. We are announcing: * Agent Protocol: a common interface for
Is a LangGraph compiled graph thread-safe / advised for concurrent use? · langchain-ai/langgraph · Discussion #1211
I just wanted to validate if it's ok to initialize/compile the graph once and then use it to serve multiple parallel requests in a web application. In other words is the shared state passed fro...
LangChain on LinkedIn: ✒️Kiroku is a multi-agent system that helps you organize and write…
✒️Kiroku is a multi-agent system that helps you organize and write documents Really complex agent (see the diagram below!) that HEAVILY involves a "human in…
A new wave of AI apps with agent-native UX is emerging, from Replit Agent to v0. Using LangGraph + 's new CoAgents extension, developers can build agent-native React applications.
In CopilotKit's blog, see how to use:
• Real-time state sharing to match user…
— LangChain (@LangChainAI)
LangGraph is one of the most versatile Python libraries for building AI agents. We can combine LangChain's LangGraph with Ollama and Llama 3.1 to build highl...
At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In this post I will dive more into memory. See the previous post on planning here, and the previous posts on UX here, here, and here.
We released a bunch of new functionality for memory in LangGraph, and in doing so we thought hard about what memory actually means, and was is useful today
Some highlights 👇
🛃Memory is application specific
The best memory today…
— Harrison Chase (@hwchase17)