Minimum Bayes Risk all the way down x.com/johnwieting2/s…

🚀 Introducing LangGraph Cloud 🚀 LangGraph helps you build reliable agents that actually work. Today, we've launched LangGraph Cloud, our new infrastructure to run fault-tolerant LangGraph agents at scale. With LangGraph Cloud, you can: • Handle large workloads with

Custom Cognitive Architectures + Generic Agent Infrastructure = LangGraph Cloud Check out the launch video here: youtu.be/l4sMKF1dTDM And blog: blog.langchain.dev/langgraph-clou… The coolest part? LangGraph Studio - an IDE or testing, debugging, and sharing LangGraph applications

LangGraph powers controllable and fault-tolerant AI workloads. I think you're gonna like it.

🦜☁️ LangGraph Cloud + Gen UI 🧬 Our latest YouTube video demonstrates how to build a fullstack app that generates charts and analyzes queries to filter and visualize data, all on the fly! You'll also learn how to deploy the app on LangGraph Cloud, our new managed service for

Jockey: A Conversational Video Agent powered by LangGraph and Twelve Labs API Jockey is an open-source conversational video agent using LangGraph's flexible agent framework and Twelve Labs (twelvelabs.io)'s advanced video APIs for intelligent video processing. LangGraph allows Jockey to

I have implemented the graph ingestion and construction part of the "From Local to Global" GraphRAG paper from Microsoft using Neo4j and LangChain . I went over all the steps and provided my detailed thoughts about the paper and underlying code. medium.com/neo4j/implemen…

🇪🇺 EU Data Residency for LangSmith 🇪🇺 We're excited to offer EU data residency to LangSmith customers on all plan tiers, at no extra cost. You can now choose to host your data in the EU (instead of the U.S.) to meet the data residency requirements of your company. LangSmith is

Meet ProLong, a Llama-3 based long-context chat model! huggingface.co/princeton-nlp/… (64K here, 512K coming soon) ProLong uses a simple recipe (short/long pre-training data + short UltraChat, no synthetic instructions) and achieves top performance on a series of long-context tasks.

Data is not the bottleneck. Reward/feedback is. Which is why anything that can be framed as a game will be solved. NP-complete?

This is my favorite thing we've launched in a while. Been using it for a week and has already changed how I build LLM apps Build your agent in code, then point LangGraph Studio at it. We'll visualize the agent, let you interact with it, and let you modify the state directly All

🚀Announcing LangGraph Studio: The first agent IDE LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications With visual graphs and the ability to

David Duong is a legend! Game changing for developer experience to be able to use the debugger locally with hot reloading

i'm losing hope rather quickly that reliable multi-hop reasoning could be solved by LLMs alone without some kind of deterministic logic engine the LLM interacts with. multi-hop reasoning is fundamentally not what LLMs are good at, and training it to do feels asymptotically

We love seeing what Rakuten is building with OpenAI and LangChain products in order to elevate their AI solutions for merchants, hotels, retail stores, and more. ❤️ Rakuten designs, tests, and continuously improves their workflow using LangGraph to build reliable agents and

Huge thank you to everyone who participated in our Agents and Compound AI Systems Hackathon this weekend with Fireworks AI and Factory! We had great talks from Harrison Chase and Eno Reyes, and saw impressive projects exploring new possibilities with agentic systems. See👇 for

🚀Excited to Introduce Coagents🚀: An innovative framework for building human-in-the-loop agents into applications - powered by LangGraph & CopilotKit. Coagents enable: - End-users to correct agent steps (in-app)🛤️ - Stream intermediate agent state 🪢 - Expose LangGraph agents

🚨 JavaScript community, get ready for a week of exciting announcements! We’re kicking off with three major updates: First, LangGraph.js 0.2 is live! LangGraph.js 0.2 is a controllable orchestration framework to build reliable agents in JavaScript/TypeScript. You can: •

AI is incredible at writing code. But that's not enough to create software. You need to set up a dev environment, install packages, configure DB, and, if lucky, deploy. It's time to automate all this. Announcing Replit Agent in early access—available today for subscribers:

Harrison Chase The team spent more time in langsmith than their significant others the past few weeks :D