memory-os vs metronix-memory
A 7-layer memory operating system for Hermes Agent: Qdrant vectors, structured facts, fabric recall, an auto-curated wiki, and surgical context injection. — versus — Self-hosted agent memory stack in Docker: Postgres + Qdrant + Neo4j hybrid retrieval, a temporal knowledge graph, ontology layer and freshness checks behind one MCP-native API.
Both are layered memory systems built on Qdrant with structured facts alongside vectors. Memory-OS is shaped for the Hermes agent specifically; Metronix targets any MCP-native agent and also ships a native Hermes provider.
| memory-os | metronix-memory | |
|---|---|---|
| Stars | 1.3k | 95 |
| Forks | 128 | 9 |
| Language | Python | Python |
| License | MIT | Apache-2.0 |
| Last activity | 2 months ago | 3 days ago |
| Topics | memory | memory, rag, knowledge-graphs |
| Curated connections | 4 | 6 |
memory-os — the curator's take
The most architecturally ambitious take on agent memory we've mapped: seven distinct layers from raw vectors to an auto-curated wiki, each with its own recall path, so the agent gets the RIGHT kind of memory injected rather than a similarity dump. The catch is coupling: it's built FOR Hermes Agent — adopting the architecture elsewhere means porting, not installing; and 7 layers is real operational surface for a ~1.3k-star project.
metronix-memory — the curator's take
Reach for it when you want one self-hosted box doing dense + sparse + graph retrieval and keeping long-lived facts fresh, and you're willing to run four datastores to get it. Skip it if you only need per-project session recall — a SQLite memory plugin is a fraction of the operational surface. Read the benchmark table with care: they are the author's own N=1 runs under a self-defined protocol, and the honest signal in them is that retrieval scores (Recall@10 85-95%) far outrun end-to-end answers (53-63%) — finding the evidence was never the hard part.