Field Watch — System

Letta / MemGPT

Last updated 20 October 2026

Why it matters

Letta's 16 March 2026 post “Our next phase” makes Letta Code, “a model-agnostic agent harness with persistent memory”, its flagship. Memory moves from database-editing tools into git-backed files (context repositories, also called MemFS), and Letta Filesystem was set to be deprecated by mid-April 2026. History: Letta's May 2025 leaderboard article describes agentic memory read, write and update tasks, and its separate August 2025 filesystem evaluation reports 74.0% LoCoMo accuracy with GPT-4o mini and constrained tool use.

Primary sources

Status

ActiveAgent harness with persistent memory (Letta Code)

Date observed: 2026-07-04

Last verified: 2026-10-20

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

Cite this page

Last updated: 2026-10-20

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 2026-10-20).

Continuity layer — this site’s working definition: A continuity layer is the part of an AI system that carries forward governed state across sessions, tools, models, and hosts: what is currently true, what changed, why it changed, by whose authority, and which evidence supports it. It sits above memory and retrieval, and below agent execution, turning stored history into usable, auditable continuity; and it can correct, supersede, revoke, expire, and forget what it carries, with evidence that it did.