Architectures
How memory systems work.
Eight ways to remember things and find them again. Read from each project’s own docs on 2026-10-04.
A system can be strong at one stage and weak at the next, which is why a single score never tells you much.
Mem0
Fact extraction
Pulls facts out of conversations and finds them again later, using meaning, keywords and entity links.
Watch for: The paid service has extras the open-source package does not. Scores must say which one ran.
Primary sourceGraphiti and Zep
Temporal knowledge graph
Stores people, things and relationships as a graph, tracking when each fact was true.
Watch for: Graphiti is the open framework; Zep is the paid service built on it. Different products.
Primary sourceLetta
Stateful agents
Gives an agent editable memory blocks that stay in its context and can be shared between agents.
Watch for: The agent's model and tools shape the result as much as the memory does.
Primary sourceCognee
Knowledge pipelines
Turns documents into searchable chunks, entities and relationships, then picks graph, vector or code context.
Watch for: The extraction model, embedder and storage backend are all part of what gets measured.
Primary sourceMemOS
Memory operating system
Treats memory as an operating system: store, retrieve, edit and delete, grouped into shareable cubes.
Watch for: Hosted, self-hosted and plugin builds differ. A score must name which one ran.
Primary sourceSupermemory
Memory API
Decides what to keep and how it connects, backed by a time-aware graph with vector and text search.
Watch for: This describes what the vendor documents. We have not verified it.
Primary sourceHippoRAG
Graph-assisted retrieval
Spreads relevance through a knowledge graph so related documents surface together.
Watch for: Finding passages and answering well are separate stages, even on the same index.
Primary sourceMnemosyne
Evidence-first memory
Keeps evidence first and builds searchable views from it, with time-aware facts and provenance. Runs on SQLite or PostgreSQL.
Watch for: This is our own system. Its own docs list unfinished parts, and it must show the same evidence as everyone else.
Primary sourceWhat each one can do
Shape, not score: can you run it yourself, does it understand time, can it say where a memory came from.
| System | Open source | Self-hosted | Graph memory | Time-aware facts | Provenance | MCP server | Best known for |
|---|---|---|---|---|---|---|---|
| Mnemosyne Operator entry | Yes | Yes | Yes | Partial | Yes | Yes | Calibrated abstention, prospective actions, auditable evidence |
| Mem0 | Yes | Yes | Partial | Limited | Limited | Yes | Simple API, wide adoption |
| Zep / Graphiti | Partial | Partial | Yes | Yes | Partial | Yes | Temporal knowledge graph |
| Letta | Yes | Yes | No | Limited | Limited | Yes | Agent-managed memory blocks |
| LangMem | Yes | Yes | No | Limited | Limited | No | Native fit for LangGraph agents |
| Cognee | Yes | Yes | Yes | Partial | Partial | Yes | Documents to knowledge graph pipelines |
| MemOS | Yes | Yes | Yes | Partial | Partial | Partial | Memory as an operating-system layer |
| supermemory | Partial | Partial | Partial | Limited | Limited | Yes | Drop-in memory API and connectors |
| OpenAI memory | No | No | No | No | No | No | Built into ChatGPT, no setup, no control |
Our own summary, deliberately rough and not verified. Spotted something wrong? Tell us.