letta
22,238Stateful agents framework with memory, reasoning, and context management (formerly MemGPT).
PreventionPre-generationFully autonomousStableTier 2AContextEnvironment
Maturity tier details
Computed tier: 2A(raw score 4.74). Effective tier: 2A.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.74
Source of truth:pipeline/maturity/score.py
Description
Letta (formerly MemGPT) introduces 'MemGPT-style' long-term memory for LLM agents: tiered context buffers, summarization, and explicit memory tools that let agents write to and retrieve from long-term storage. Addresses runaway context pollution.
Why it's included
Memory/context-management cell — supervision as bounded-context discipline rather than runtime gating.
Addresses failure modes
- Context pollution — Trajectory drift, hallucination spirals, overlong or off-task context.
- Scope creep — Actions outside declared task boundary.
Techniques
tiered-memorysummarizationmemory-tools