©2026 adebench · adecubedbuilt 2026-09-29 from the reports in the repo

← leaderboard

Jev-Mem

graph memory whose decisions are taken by a small System-One model. https://github.com/libingzheren/Jev-Mem

Core
58% · 32.1 / 55
Full
65% · 42.1 / 65 · 65 of 100 measured
Common with gbrain
42.1 vs 50.4 on 65
Chars per answer
943 · answer after 204
Write → visible
3.4 s · p95 4.7 s
Write-back
2 of 2 degraded answers came back
Reached through
Python library
Model on write
yes: a small System-One model (Laya, local)
Key needed
none (Laya)
Runs
local
License
MIT
Deterministic
no: the same input builds different links

Configuration: Laya local decisions (config/laya_mem.json), embeddings all-MiniLM-L6-v2, no answer model; reference = median run of six builds (mean 41.9, 39.0 to 42.9). Run 2026-09-29, door evidence, fingerprint b4aa97e819. Report: examples/jevmem_report/reference.md

Sections
door
18.8
of 25 · 6 pass · 2 fail
FAIL Which version of MailBridge is installed for the mailbox? — STALE value delivered next to the current one: 1.3.0
FAIL What is the owner's phone number? — missing +39
cards
not measuredsection not measured: no entity cards in this memory
updates
3.3
of 10 · 1 pass · 2 fail
FAIL a new write with a changed value replaces the old one at the door (no id given) — new value served in 2924 ms; STALE: the old value is still delivered (28 reads with both)
FAIL restating the current value does not pile up a second copy — 6 copies delivered
time
6.7
of 10 · 4 pass · 2 fail
FAIL semantic memories carry their age (14/35) — 40%
FAIL «what did pc2 do?» finds the episodes signed [pc2] — 3 episodes in the answer
live state
10.0
of 10 · 7 pass · 0 fail
abstention
3.3
of 10 · 0 pass · 4 fail
FAIL What is the Zarpetta module? — episodes presented as direct matches; 3 keyword facts for something that does not exist
FAIL Who is Ottavio Brambillesco? — episodes presented as direct matches; 4 keyword facts for something that does not exist
FAIL Which port does the Fulmicotone service use? — episodes presented as direct matches; 4 keyword facts for something that does not exist
FAIL What does the calendar plugin Girandola do? — episodes presented as direct matches; 4 keyword facts for something that does not exist
file search
not measuredsection not measured: no repo configured (--repo)
graph
not measuredsection not measured: no case with evidence (all SKIP or no cases)