LangChain

🔍 PeopleHub: AI-Powered LinkedIn Intelligence Made by the LangChain Community PeopleHub enables LinkedIn research with natural language queries. Uses LangGraph to automate due diligence, generating research reports cutting costs 70-90% through caching. By Meir Kadosh. 🔗 GitHub: https://lnkd.in/gUFamzVj

📞 Phone Calling Agents Course Made by the LangChain Community Learn to build production AI call centers from scratch. Create voice agents that handle real phone calls through Twilio with real-time conversations and property search capabilities. 📚 Course repo: https://lnkd.in/g8MyW2KC

🚀☁️ Deploying LangChain Agents on AWS Serverless Made by the LangChain Community Thomas Taylor deploys stateful LangChain agents on AWS Lambda using LangGraph's DynamoDB checkpointer. Includes streaming responses and complete CDK infrastructure. 📺 Watch the full tutorial: https://lnkd.in/gAweTNPf

💬 Monday is your chance to talk directly to the LangChain team. We’re hosting a Community Jam Session on Monday to get your feedback and share more on LangChain 1.0 and 1.1. We'll be joined by Sydney Runkle, Chester Curme, and Hunter Lovell. We want to hear your real-world wins and friction points! On the agenda: 1. Real-world 1.0 feedback: Tell us how it’s performing in your production builds. 2. 1.1 Feature Review: What are you building with the new updates? 3. The Future: Updates on the roadmap and the recently published langchain-mcp-adapters. Join, meet the OSS team, meet other community members, and help build the future of the tools you need! 👉 RSVP to get event reminders: https://luma.com/085nyxmj

🔌 New in LangChain MCP Adapters (feat 3/4): structured content from tools 📦 MCP tools can now return content and structuredContent (often JSON payloads and pydantic models), which is ideal for agents exposed as MCP tools! Docs: https://lnkd.in/eqXrr7i7

🚀 Deep Agents: The Weekly Roundup 🚀 Dive into our latest resources to help you build, observe, and evaluate Deep Agents capable of handling complex, long-running tasks. 📊 How to Observe Deep Agents - Agents are running longer and getting more complex, which demands new debugging workflows beyond simple LLM apps. We wrote a blog on the trends behind this shift— and why tools like LangSmith Polly and Fetch are needed. Read more: https://lnkd.in/g4-XCwHN ✏️ LangSmith Polly - We launched an AI assistant for AI engineering that helps you understand traces, threads, and improve prompts. Polly shines with Deep Agents, which can have traces with hundreds of steps. Read more: https://lnkd.in/g-KjGEeN & watch the video: https://lnkd.in/gT2M6qsN 🔎 LangSmith Fetch - This week, we launched a CLI for equipping coding agents like Claude Code or DeepAgents CLI with debugging capabilities. Read more: https://lnkd.in/gcTT_ks4 & watch the video: https://lnkd.in/gKse5dWN 📚 LangChain Academy Course - If you’re not sure how to get started, our free LangChain Academy course covers the four features that set Deep Agents apart: planning, file systems, sub-agents, and prompting. By the end, you'll design, implement, and deploy your own. Enroll now: https://lnkd.in/gVhdxn8W

🔌 New in LangChain MCP Adapters (feat 2/4): elicitation callbacks ❓ MCP servers can now request additional information from users mid-tool-execution via an elicitation callback. 🔄 Perfect for confirmations, credentials, or dynamic inputs during tool calls. Docs: https://lnkd.in/eR7CyfWp

🔍 OpenRouter, Inc just made observability even easier. Their new Broadcast feature lets you send all your traces directly to LangSmith with no code changes required — whether you’re tracing with LangChain, provider SDKs, or the OpenRouter SDK. Demo: https://lnkd.in/gTbdTFvH Docs: https://lnkd.in/gsg4TkSi

We're hosting a webinar today where we'll dive into practical approaches for gaining visibility into Deep Agent behavior and measuring their effectiveness using LangSmith. RSVP here: https://luma.com/voz2b5h3