![Cover Image for LlamaIndex Webinar: Open-Source Longterm Memory for Autonomous Agents](https://cdn.lu.ma/cdn-cgi/image/format=auto,fit=cover,dpr=2,background=white,quality=75,width=400,height=400/event-defaults/1-1/standard5.png)
![Cover Image for LlamaIndex Webinar: Open-Source Longterm Memory for Autonomous Agents](https://cdn.lu.ma/cdn-cgi/image/format=auto,fit=cover,dpr=2,background=white,quality=75,width=400,height=400/event-defaults/1-1/standard5.png)
LlamaIndex Webinar: Open-Source Longterm Memory for Autonomous Agents
In this webinar we're excited to host the authors of memary - a fully open-source reference implementation for long-term memory in autonomous agents 🧠🕸️
In this session, we'll dive deep into how memary works:
1️⃣ Extracting agent inputs/responses into a knowledge graph using LLMs and neo4j, which also serves as a searchable tool for the agent
2️⃣ Utilizing a memory stream to capture interaction timelines and extract themes
3️⃣ Ranking popular entities in an entity store and feeding them into the agent's context window.
We'll also have a deeper discussion and Q&A session around memory, including challenges and future directions.
Join Julian Saks, Kevin Li, Seyeong Han, and the rest of the memary team as they share their insights on pushing the boundaries of long-term memory in autonomous agents.