All comparisons
Heartwood Memory comparison

Heartwood vs Letta — provable memory vs the stateful-agent framework

Naming: “Letta” is the current framework name; “MemGPT” now refers to the original research/design pattern. Use “Letta”; “formerly MemGPT” appears once for search.

TL;DR

Letta is a platform for building and operating stateful agents with self-editing, persistent memory blocks (the framework formerly known as MemGPT). Heartwood is a governed memory store: signed records, policy-before-ranking, and a re-executable key-destruction proof. They solve adjacent problems — Letta runs the agent; Heartwood governs the memory.

At-a-glance table

Heartwood Memory compared with Letta
AxisHeartwood MemoryLetta
Governance granularityPer individual memory recordNot evaluated in public docs (pricing lists RBAC; detailed RBAC page currently 404s)
Provenance signingPer-record Ed25519, fail-closed readNot evaluated in public docs
Tamper-evident auditHash-chained audit logNot evaluated in public docs
Policy-before-rankingYesNot evaluated in public docs (core blocks are always-visible)
Erasure / RTBFCrypto-shred + key-destruction proofBlock/archival-passage/agent deletion APIs (not cryptographic or verified RTBF)
InterfacePython library + governed MCP serverTypeScript/Python SDKs and REST API; MCP/external DBs as tools
DeploymentSelf-hosted, embeddedOpen-source self-hosted Docker/server, or managed Letta cloud
LicenseSource-available (BSL 1.1); 0.1.x MITApache-2.0 (Letta repo); managed service terms separate
PricingFree / Team $349·mo / Pro $6,000·yr (early access)Free $0 / Pro $20·mo / API Plan $20·mo + usage / Enterprise custom
Best-forRecord-level, re-executable proofBuilding/operating stateful agents with self-editing memory

“Not evaluated in public docs” = not found in Letta's current primary documentation as of 2026-07-15; it is not a claim the feature is absent. Vendor pricing reverified immediately before publish.

Comparison by dimension

Different layer

Letta is an agent framework/runtime; Heartwood is a governed memory store. The honest comparison is “run the agent” vs “govern its memory” — they can compose.

Deletion & governance

Letta documents block, archival-passage, and agent deletion APIs — but not cryptographic or verified RTBF, and its detailed RBAC page currently 404s, so governance granularity couldn't be verified. Heartwood adds a per-subject key-destruction proof and per-record policy.

Who Letta is best for

Teams building and operating stateful agents with self-editing, persistent memory.

Who Heartwood is best for

Teams that need a governed, provable memory layer under whatever agent framework they run.

Can Heartwood run underneath Letta?

As the governed memory store behind the agent's memory calls (shape-compatible example contract, not an official integration).

See the governed-memory model

FAQ

Is Letta the same as MemGPT?

Letta is the current framework name; MemGPT names the original research pattern.

Is Letta open source?

The Letta repository is Apache-2.0; managed service terms are separate.