Recorded run, 75 questions

Did the right memory come back?

XERJOther projects

Right answer in the top 5, all questions, %

XERJ, semantic, MiniLM94.7
XERJ, hybrid, MiniLM93.3
ReMe, hybrid, MiniLM93.3
mcp-memory-service, default, MiniLM89.3
Mem0, infer=False, MiniLM88.0
Mem0, infer=True, Qwen2.5 3B86.7
MemPalace, default, MiniLM84.0
agentmemory, default, no key74.7
XERJ, BM25, default recall73.3
ReMe, default, BM2570.7
XERJ, hybrid + recency 0.368.0
memvid, default, lexical1.3

New value ranked above the old one, 15 updated facts, %

XERJ, hybrid + recency 0.393.3
Mem0, infer=True, Qwen2.5 3B20.0
ReMe, default, BM2520.0
XERJ, BM25, default recall13.3
XERJ, semantic, MiniLM13.3
XERJ, hybrid, MiniLM13.3
Mem0, infer=False, MiniLM13.3
MemPalace, default, MiniLM13.3
ReMe, hybrid, MiniLM13.3
agentmemory, default, no key13.3
mcp-memory-service, default, MiniLM6.7
memvid, default, lexical0.0

Drawn from out/summary.csv in benchmarks/agent-memory. Bars start at 0 and the full width is 100%. Every setup got the same 85 memories in the same order and the same 75 questions, with k = 5.