Our agent memory: memory-graph retention measured

Our agent memory: memory-graph retention measured reports operational numbers measured directly on our ai-server (Hax) stack, and — instead of dumping figures — explains what each number actually means for a real decision. Even if you are new to running local AI, this single post should let you grasp 'what do I decide when I see this number' in about five minutes.

What these numbers mean#

저장 9147개 중 활성 8919개로 생존율 97.5%, 무효화는 228개(2.5%)뿐이다. 에이전트 기억이 거의 썩지 않는다는 뜻이며, 무효화율이 낮다는 건 저장 시점의 신뢰도 판정이 잘 작동한다는 신호다 — 기억 그래프를 신뢰 기반 의사결정에 쓸 수 있다.

How we measured it (reproducible conditions)#

These are not vendor specs or marketing figures; they are values we measured ourselves under the conditions below. We list the conditions because when the conditions change, the numbers change too — cold start versus warmed up, batch size, and the exact hardware all shift the result for the same model. So we state reproducible conditions (measured 2026-07-04):

• bench_harness.probe_curator (curator stats 실측)

Rather than memorizing a single number, understand it together with these conditions, so you can diagnose for yourself why your own environment produces a different value.

How to use this in practice#

The derived judgment above translates straight into an operating decision. The point is not to memorize raw figures but to read the relationships between them — a ratio of two values, a utilization rate, a cross-check — because those relationships tell you what to scale up and what to conserve. We use this to check existing headroom before buying new hardware, and to split workflows into a fast path and a quality path. The same logic applies directly to your own local AI setup.

Why this beats vendor specs#

These are values measured in our own operating environment, not vendor sheets or someone else's benchmark. Every number above is measured (not estimated), with date and source (Hax /data). Unlike generic AI-written prose, this derived judgment cannot be produced without the measurement. Only our own measured values are used; no private tokens or internal paths are exposed.

Note: the values above are our own stack measurements as of 2026-07-04 and are refreshed when conditions change (measured values only, no estimates).

Related reading: ob-gemma4-moe-ours-cost ai-server Gemma MoE GPU 2026 복구 실측, mac-mini-14b-1600-70b-2026 Mac Mini on-device hardware 2026

Full guide: 노트북에서 AI 모델 뭐가 돌아갈까 — VRAM·RAM 실측과 메모리 구조

References#

• Hax data