The Continuity Layer

Field Watch — System

Letta / MemGPT

01

Why it matters

A public leaderboard scoring models on agentic memory read/write/update tasks, from the team behind the MemGPT/Letta agent memory framework.

02

Primary sources

03

Status

ActiveAgentic memory framework + evaluation

Date observed: 2026-07-04

Last verified: 2026-07-05

How entries are chosen, categorized, and re-checked: How the map works.

Cite this page

Last updated: 2026-07-05

Maintained by: The Continuity Layer

How to cite: Cite the specific page and section (e.g., “The Continuity Layer, Letta / MemGPT”), not the site as a general source. Attribute to The Continuity Layer.

Canonical URL: https://thecontinuitylayer.com/field-watch/letta-memgpt

Suggested citation: The Continuity Layer. “Letta / MemGPT.” https://thecontinuitylayer.com/field-watch/letta-memgpt (last updated 2026-07-05).

Continuity layer — canonical definition: A continuity layer is the part of an AI system that carries forward governed state across sessions, tools, and models: what is currently true, what changed, why it changed, and which evidence supports it. It sits above memory and retrieval, and below agent execution, turning stored history into usable, auditable continuity.