Why Your AI Agent Gets Brain Damage, and How to Fix It - Tyler Barnes, Mastra
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
The compaction problem
Meet Tyler Barnes, Mastra founding engineer
Mastra Memory v1
The jump to observational memory
What is LongMemEval?
How OM works
Recall: searching your own history
Observational memory extractors
Subconscious OM & the knowledge graph
Agent signals: decoupling the loop
State signals & connecting the graph
The "dungeon" days
More episodes
- September 9, 2026GPT-6 Astra vs Claude Fable 5.1, We Should Pause AI & The Benchmark Wars | This Week In AI
- September 8, 2026Multiplayer Coding Agents in the Cloud - Charlie Holtz, ConductorCharlie Holtz
- September 3, 2026OpenAI Cuts Off Cursor, Nvidia Buys Hugging Face, Ox Alpha is GLM | This Week In AI
- August 28, 2026Why Agents Are Actually Workflows - Tony Kovanen, Mastra's Founding Engineer