Back to Arena

Memary

by Kingjulio8238

System Card

OrganizationKingjulio8238
Released2024-04
Architecturegraph-rag / Knowledge graph + Llama-Index
DetailsBuilds a Neo4j knowledge graph of entities and relations extracted from agent traces, paired with a Llama-Index retriever. Designed as a drop-in long-term memory layer for autonomous agents.
Parameters—
Domainagent-memoryknowledge-graphlifelong-learning
Open SourceYes
CodeRepository
neo4jllama-indexagentopen-source

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Data Transparency:2 self-reported4 estimated
Long-Context Retrieval
0/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
no data
Multi-Turn Recall
1/2
LoCoMo
71.729pEstimated
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
75.550pEstimated
Multi-Hop QA
3/3
BABILong
76.863pEstimated
MultiHop-RAG
52.70pSelf-Reported
HotpotQA
54.26pSelf-Reported
Agent Task Memory
1/1
AgentBench-Mem
7226pEstimated
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Memary repo evalsArena estimate — derived from capability profile, not independently verified