🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

☎️Vodafone transforms data operations with AI using LangChain and LangGraph I've been super impressed working with the Vodafone team on their GenAI initiatives. Read here about how they stood up a multi-agent system performance metrics monitoring blog.langchain.dev/customers-voda…

Exciting to see LangChain on this list, even more exciting to see so many startups powered by LangGraph/LangSmith on here as well!

⚡💬 Optimistic UI in useStream() Update frontend state before network requests are fired to make your app feel lightning-fast, like showing user messages in chat history right after submission.

OpenAI recently released a guide on building agents which contains some misguided takes There's a lot of FUD, confusion, hype, and noise around agents I wrote a blog on how to think about agent frameworks. Includes: Background Info - What is an agent? - What is hard about

Marc Klingen Sam Bhagwat Abhi Aiyer Riqwan Mastra I don’t mean to make even more hot takes on a sunny Sunday but… Tracing/evals is so core to building agents that if you’re a framework and you’re not building your own I don’t take your framework seriously 🤷‍♀️ A lot of newer frameworks (openai, google, pydantic, mastra) all do

sent Harrison Chase, CEO of LangChain a message explaining the problems we were facing building with langgraph. He responded within the hour, connecting us to his engineering team, who were immensely helpful. I find this more valuable than having a perfect product.

🚨Catch Production Failures Early with Alerts in LangSmith Set up real‑time notifications on error rates, run latency & feedback scores to spot failures before your customers do. If you’re already sending production traces to LangSmith, set up your first alert today:

Excited to share new levels of visibility for agents that we’re launching to help you understand what your agent is doing! You can now get visibility into tool calls and run stats: ⬆️ View the most popular tools and runs ⏱️ Get insight into latency of those tools and runs ⚠️

More agents are being deployed in production (we are seeing this too!) A bunch of launches from Langchain around observability in Langsmith!

Our own Harrison Chase is up first at Interrupt 2025 🦜🔗! - Agent observability in LangSmith around tools and trajectories - LangGraph Studio V2 - Open Agent Platform (low/no code templates, MCP tool servers) - LangGraph Platform is now GA Agents are here. More updates in 🧵👇

LangGraph Platform is now generally available! 🚀Deploy, scale, and manage agents with LangGraph Platform — built for long-running, stateful workflows. You can: • 1-click deploy, horizontally scale, and leverage comprehensive APIs including memory, HIL, and conversational

Super excited to finally release Open Agent Platform! We've been building UI/UXs for agents for over 6mo now, and OAP brings them all together, in a seamless, no-code platform! Open source repo, and a public demo in reply👇

That's a wrap on Interrupt 2025! 🚀 🌎 800 agent engineers from across the globe gathered in San Francisco for LangChain's first industry conference to hear stories of teams building agents – and we’re still riding the high! Cisco, Uber, Replit ⠕, LinkedIn, BlackRock,

🚨 LangGraph open source release week coming up! Teasing new features with emojis - any guesses? Monday: ♻️ Tuesday: 🕰️ Wednesday: 🤝 Thursday: 💻 Friday: 🔍

langsmith really is a fantastic product it just feels so natural to use, so obvious its like mac for llms - everything just works as you would expect it to if you ever built a product for real users you know how hard it is to achieve this

🛡️ Introducing LangChain Sandbox: run untrusted Python safely in your AI agents! 🔒 Isolated execution environment with configurable permissions 💻 No remote execution or Docker containers needed 🔄 Persist state across executions using sessions youtube.com/watch?v=FBnER2…

If you interact with a chat agent, it's usually a one-to-one experience—you're doing one thing at a time. With ambient agents, however, there can be thousands running in the background, dramatically scaling our ability to leverage AI. LangChain's Harrison Chase at AI Ascent.

Not all SWAG is created equal! My boys insisted brining their LangChain parrots camping this weekend! Does the parrot have a name?

LangChain Availability Impacted: Please follow our status page for more information status.smith.langchain.com We've identified an underlying cloud provider issue causing failures in the LangSmith application, API, and LangGraph Platform including run ingestion. We are working

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks.