MemOS (Agent / long-term memory): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 2 beat it on benchmarks — #23 of 63 most-superseded. Sub-problem: cluster led by Nemori. Newer alternatives in the same sub-problem include HAGE, SmartSearch, event-centric memory.

Superseded baseline#23 of 63 most-superseded

MemOS

MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models

Agent / long-term memory · first seen May 28, 2025

superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 2 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating MemOS. Values are copied from the source paper's tables — verify against the cited paper.

MemGuard beats MemOS · Acc. (%) [HaluMem extraction]
89.53 vs 59.55
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
MemGuard beats MemOS · C [HaluMem update]
70.79 vs 62.11
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
SmartSearch beats MemOS · Overall [EverMemOS protocol (gpt-4.1-mini)]
93.5 vs 80.8
SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
SmartSearch beats MemOS · Overall [full benchmark]
88.4 vs 77.8
SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.