Letta.

TL;DR — Letta is an agent runtime focused on persistent memory and stateful agent behavior across sessions.

What it is

It gives agents explicit memory blocks and control over what is stored, summarized, or recalled.

Why it exists

Stateful agents need durable, inspectable memory design. Letta makes memory a first-class runtime concept.

Install

pip install letta

Basic usage

# create agent with persistent memory
# run multi-session conversations with state recall

When to use, when to skip

Use it when this category is a bottleneck in your agent stack and you want faster delivery with fewer custom components.

Skip it when your workload is tiny, requirements are fixed, or a plain provider SDK plus a few local functions is enough.

Alternatives

Compare with adjacent tools in the same AI Native category and choose based on interface style, deployment model (hosted vs self-hosted), and team familiarity.

Verified against project documentation, June 2026.