LangChain NY Meetup: LLM Wikis and Managing Agent Context

​Join us for an meetup in New York with Brace Sproul (Head of Applied AI at LangChain), and Daniel Shea (Deployed Engineer at LangChain) where we'll dive into how to manage agent context.

​Most agents fail not because the model is weak, but because it doesn't have the right context. LLM wikis are emerging as a common pattern for solving this: a structured knowledge base an agent can query to understand a codebase, product, or domain. LangChain recently open sourced OpenWiki, a project for building and maintaining your own LLM wiki. Agent harnesses are also an important part of managing agent context. Harnesses with open memory standards allow you to bring your own storage and own your data.

​This meetup will feature two talks. First, Brace will break down how to actually build these systems, and whether "wiki" is even the right way to think about them. Then, Daniel will cover how to build memory-first agents with Deep Agents, LangChain's open source agent harness. He'll walk through the memory layer from first principles — why filesystem-backed memory gives you flexibility without lock-in, and why that matters as agents move to production.

​Agenda ⏰
​6:00 PM: Welcome + Food/Drinks
6:30 PM: Presentation with Brace Sproul (LangChain) - LLM Wikis and Giving Your Agents Memory with OpenWiki
6:50 PM: Q&A Session with Brace
7:00 PM: Presentation with Daniel Shea (LangChain) - Memory is the Moat
7:15 PM: Q&A Session with Jacob
7:25 PM: Networking
8:30 PM: Event Ends​

Event info:
​🎤 Please note this event is fully in-person and will not be live-streamed or recorded.
​​📍 Location: Address is in Downtown Manhattan and will be send out to approved registrants.
​🎟️ We can only admit guests with approved registrations. If you’re still on the waitlist or haven’t received a confirmation yet, please stay tuned for future events—but please sit this one out.

About the host:
LangChain powers the full agent development lifecycle — building, testing, deploying, and monitoring — so AI teams can improve their agents systematically. LangSmith Engine accelerates this cycle, automatically surfacing and fixing issues to improve agents over time. LangSmith is neutral by design, so teams can customize their own stack to optimize on cost and performance as the landscape evolves. More than 7,000 customers, including Nvidia, Bridgewater, LinkedIn, Workday, Harvey, and Rippling trust LangSmith to build and manage their agents. Learn more: www.langchain.com