---
title: "Letta vs Mem0"
url: https://memory.wiki/ycd01N9A
updated: 2026-05-10T15:36:24.301Z
hub: https://memory.wiki/hub/yc-demo
bundle_count: 1
concept_count: 12
source: "memory.wiki"
---
# Letta vs Mem0

| | Mem0 | Letta |
|---|---|---|
| Storage | Vector + graph | Hierarchical (core / archival) |
| Authorship | Auto-extract | Auto-extract + manual edit |
| Hosted | Yes | Yes + self-host |
| Format | JSON memories | Block-based |
| OSS | Yes | Yes (formerly MemGPT) |

## Where they differ
Letta inherits MemGPT's "context windows are an OS resource" framing —
core memory (always loaded) vs archival (paged in). Mem0 is flatter:
all memories are vectors, top-K retrieved per turn.

## Where they're similar
Both treat memory as something the system *extracts from* the user's
behavior. Neither makes memory addressable as a URL the user can paste
into a different AI.


---

## Concepts in this document
- **mdfy.app** _(entity)_
  Core platform enabling document import, AI structuring, and multi-format export.
- **mdfy** _(entity)_
  Alternative approach emphasizing author-owned memory and cross-platform sharing via URLs.
- **WYSIWYG editing** _(concept)_
  Allows users to edit directly in the rendered preview using contentEditable, bridging the gap between visual and source editing.
- **Mem0** _(entity)_
  AI memory platform using flat vector-based storage with top-K retrieval for memory recall per turn.
- **Letta** _(entity)_
  AI memory system inheriting MemGPT's hierarchical context-window architecture with core and archival memory tiers.
- **Claude** _(entity)_
  Mentioned as alternative AI platform that cannot access ChatGPT memories.
- **ChatGPT** _(entity)_
  Example AI system that can consume mdfy hubs via URL paste.
- **Vendor lock-in** _(concept)_
  The central argument that proprietary memory systems create strategic dependency on a single platform.
- **AI integration** _(concept)_
  MCP Server and AI provider abstraction enabling connection with ChatGPT, Claude, Gemini and other AI tools.
- **User-authored memory** _(concept)_
  The proposed alternative model where users control memory content rather than relying on extraction models.
- **AI Memory Systems** _(concept)_
  Core concept of how AI systems store and retrieve conversational context and learned information about users.
- **pgvector** _(entity)_
  Vector storage technology used by mdfy for managing 1536-dimensional embeddings.

## Concept relations (within this doc's concepts)
- **Mem0** similar to **Letta**
- **Vendor lock-in** controls access **AI Memory Systems**
- **Mem0** architectural alternative **Letta**
- **mdfy.app** implements **WYSIWYG editing**
- **mdfy.app** provides **WYSIWYG editing**
- **AI integration** extends capabilities of **mdfy.app**
- **mdfy** stores embeddings in **pgvector**
- **User-authored memory** core principle of **mdfy**

## Bundles containing this document
- [AI Memory Stack](https://memory.wiki/b/ycb00hEg)
  > Notes and references about AI memory systems including Mem0, Letta, OpenAI Memory, LLM Wiki, embeddings, and vector DBs. Background reading for the Memory.Wiki architecture.

_Hub canonical:_ https://memory.wiki/hub/yc-demo
_Concept digest:_ https://memory.wiki/raw/hub/yc-demo?digest=1&compact=1