Back to all episodes

Why Your AI Agent Gets Brain Damage, and How to Fix It - Tyler Barnes, Mastra

September 15, 2026

Tyler Barnes is a founding engineer at Mastra and the person behind its memory systems. In this chat with Shane, he explains observational memory — Mastra's fix for the thing every coding agent does where it fills up its context, compacts, and forgets what you were doing. A background agent watches the conversation and writes short observations, which replace bulky tool calls and messages in context, so you keep what matters and drop the noise. It scored state-of-the-art on the LongMemEval benchmark. Tyler also covers recall, extractors, subconscious memory that builds a knowledge graph, and agent signals for steering an agent mid-task.

Watch on

Episode Transcript

00:00

The compaction problem

00:19

Meet Tyler Barnes, Mastra founding engineer

01:39

Mastra Memory v1

03:47

The jump to observational memory

04:24

What is LongMemEval?

05:07

How OM works

11:00

Recall: searching your own history

12:09

Observational memory extractors

14:01

Subconscious OM & the knowledge graph

16:49

Agent signals: decoupling the loop

20:23

State signals & connecting the graph

21:26

The "dungeon" days