Kick off ElasticON week with the Elastic NYC User Group and Pulumi at our special pre-ElasticON NYC meetup on Tuesday, October 6!
Engin Diri from Pulumi and Ines Potier from Elastic will share technical talks, followed by pizza, refreshments, and networking with the New York City tech community.
🎟️ Continue the experience at ElasticON NYC
ElasticON NYC takes place on Thursday, October 8, and registration is free! Connect with Elastic experts and the community, gain hands-on experience, and discover how the Elasticsearch Platform powers real-world AI, search, observability, and security solutions.
[Register for ElasticON NYC here](https://www.elastic.co/events/elasticon/new-york-city?utm_source=luma&utm_medium=event_page&utm_campaign=elasticon_nyc_2026&utm_content=pre_elasticon_meetup_oct6)
📅 Date: Tuesday, October 6th from 6:00-8:00 PM
📍 Location: Elastic NYC Office
1250 Broadway, Floor 16, Training Room
New York, NY 10001
🎤 Want to present at our next meetup?
Are you interested in presenting your Elastic use case? We welcome 5-10 minute lightning talks, 45-minute deep dives, and everything in between. If you're interested, please send us an email at [meetups@elastic.co.](http://meetups@elastic.co./)
📝Agenda:
• 6:00 pm: Doors open; say hi and eat some food
• 6:30 pm: Give Your Coding Agent an (Elastic) Memory - Engin Diri (Pulumi)
• 7:10 pm: Talk # 2 - Details coming soon - Ines Potier (Elastic)
• 7:30 - 8:00 pm: Networking and event wrap-up
💭 Talk Details:
Give Your Coding Agent an (Elastic) Memory - Engin Diri (Pulumi)
*If you work with a coding agent every day, you know the routine. Each new session starts blank: the agent re-reads files it read yesterday, asks about decisions you settled last week, and redoes debugging you already finished. Its only memory is the context window, and that empties every time you close your laptop.*
*Claude Code ships a built-in fix: markdown notes the agent writes for itself and reads back at the next session start. It helps, but the notes live on one machine, there is no real search, and anything past the first page of the index gets dropped.*
*agent-memory, an open source project based on Elastic, takes the same idea further: memory lives in Elasticsearch, where decisions, tasks, and session history are searchable and shared across machines. I'll run both side by side, kill an agent mid-task, and show how much more a fresh one remembers when its memory is a search engine instead of a text file.*
*And here comes Pulumi: one command creates everything in Elastic Cloud, it lives in a repo you can review, and every teammate gets an identical memory backend instead of their own snowflake. No promises about becoming a 1000x AI engineer, but your agent will stop asking you the same question twice.*
