LangChain

Setup OpenWiki once, then forget about it. It'll automatically update its docs as you make changes to your codebase OpenWiki is the easiest way to increase your coding agent performance, and it's fully OSS: - open harness (deepagents) - open CLI/workflows (OpenWiki repo) - runs on open models (GLM 5.2, Kimi K2.7, etc) Checkout the OSS repo: https://lnkd.in/g-czXxQe

Your coding agent bill doubled and nobody can tell you why. Here's the actual reason: Claude Code, Cursor, and Copilot all log activity in different formats. The second your team uses more than one (they will), your visibility goes to zero. We built LangSmith to fix this. It traces Claude Code, Codex, Cursor, Copilot, Pi, and OpenCode into one consistent format. ✅ Same trace tree ✅ Same metadata ✅ Same query syntax …regardless of which tool actually ran the session. Everything you need to know: https://lnkd.in/gcmzaddv

In the latest episode of the Max Agency podcast, Harrison Chase sits down with Benjamin Tannyhill, Product Manager at LangChain for a deep dive into how we built LangSmith Engine - our agent for agent engineering.

Interrupt 2026 is expanding beyond San Francisco. We're bringing The Agent Conference by LangChain to New York City and London this fall. Here's what to expect: → Hear from engineers and teams shipping agents in production → Keynotes from Harrison Chase + industry leaders on what's next for agents → Hands-on workshops with LangChain product experts → First look at new LangChain products Tickets go on sale next week and seats are limited. Sign up to get notified when tickets drop: https://lnkd.in/gzXMaRig

🗣️ Our first LangChain community meetup is coming to the DMV! 🏛️ Join us and G2X | GovCon GTM Platform in Washington, DC on July 30 for a builder-focused evening on using Deep Agents to solve complex GTM research workflows. Bring your questions, your projects, and your fellow builders. Whether you're already building with LangChain or just getting started, this is the room to be in. Ron Jones Haitham S. #langchain #deepagents #aiagents #dmvtech #govtech Grab a spot and RSVP 👇

OpenWiki can generate repo docs, automatically update them as your codebase evolves, and do Q&A over your docs and codebase! Built on DeepAgents, try it for free, locally today: https://lnkd.in/g-czXxQe

Excited to release OpenWiki! OpenWiki is the easiest way to generate and maintain documentation in your codebase, built specifically for agents to consume Checkout the blog on it: https://lnkd.in/gp7pkQkT

Sometimes, you need to run agents in a real, reproducible, isolated environment, many times in parallel, with a deterministic check at the end. Harbor solves this problem and is now wired directly into Deep Agents, LangSmith Sandboxes, and LangSmith Observability. https://lnkd.in/g_Hyd-Pm Want to get started? Nicholas B. put together a 10 minute overview that runs through everything you need to know, including: ✅ What is Harbor? ✅ How to integrate a Deep Agent with Harbor ✅ How to view results in LangSmith

You can now run recursive language model (RLM) workflows in Deep Agents. Here’s how this works. Instead of fitting the full input into a context window, the model uses a code interpreter to dispatch subagents recursively over chunks of the context. Sydney Runkle put together a blog and video that walks through: ✅ How RLM workflows work in Deep Agents ✅ Why you may want to use an RLM ✅ What happened when we ran it on OOLONG ✅ How you can get started https://lnkd.in/gxGnXY4N