The Agentic World #2

The Agentic World #2: Agentic Memory

Giving agents memory is easy. Making that memory trustworthy is harder.

About

AI agents are getting memory. They can remember conversations, learn from previous interactions, retain preferences, and use past experiences to make future decisions.

But remembering something and remembering it correctly are two very different things.

What happens when an agent remembers something that is no longer true? When two memories contradict each other? When an incorrect memory influences every decision that follows?

As agents move from completing individual tasks to operating autonomously over weeks and months, memory becomes critical infrastructure. The challenge isn't simply storing more information. It's building systems that know what to remember, what to retrieve, what to update, and when to forget.

The Agentic World #2 is about building agent memory that actually works.

We'll explore different approaches to memory through working demos and architectural perspectives — from knowledge graphs and multimodal memory to procedural memory that helps agents remember how work gets done.

Because an agent is only as trustworthy as the memory it relies on.

On Stage

Keynote 1: Knowledge Graphs as a Reliable Memory Base for Agents

Aditya Shrivastava, Applied AI Engineer, HydraDB

Aditya will show how knowledge graphs help agents structure relationships across people, events, and past interactions — improving retrieval, ambiguity resolution, and long-term reasoning.

Keynote 2: Multimodal Memory for Agents

Vishakha Gupta, Founder, ApertureData

Vishakha will explore how agents can turn images, videos, documents, and other multimodal data into searchable memory that can be retrieved and reasoned over.

Keynote 3: Procedural Graphs — Remembering How, Not Just What

Amitabh Das, Founder, AgentOS

Amitabh will introduce procedural graphs: memory structures that capture actions, tools, dependencies, and successful execution paths so agents can remember not just information, but how to get things done.

What We'll Explore

Across the demos and discussions, we'll look at questions like:

• How should agents structure long-term memory?

• How do knowledge graphs improve retrieval and reasoning?

• How can agents work with multimodal memory?

• How should memory evolve when information changes?

• What happens when memories contradict one another?

• Can agents remember successful workflows instead of rediscovering them every time?

• How should systems decide what to preserve, update, or forget?

Schedule

• 6:00 – 6:15 · Doors and introductions

• 6:15 – 6:35 · Aditya Shrivastava — Knowledge Graph Memory

• 6:35 – 6:55 · Vishakha Gupta — Multimodal Memory

• 6:55 – 7:15 · Amitabh Das — Procedural Graphs

• 7:15 – 7:45 · Agentic Memory Demos and discussion

• 7:45 onward · Drinks and networking

Who It's For

Founders, AI researchers, engineers, and anyone building agents that need to remember, learn, and operate reliably over time.

Whether you're building memory infrastructure, autonomous agents, knowledge graphs, multimodal systems, retrieval systems, or figuring out how to move agents from demos into production, this room is for you.

Details

📅 Thursday, 2026
🕕 6:00 PM
📍 San Francisco
🎟️ Free. Seats are limited.

Come see the different ways agents can remember — and what the emerging memory stack might actually look like.