Context-plane hygiene for LLM agent stacks · live at sweap.it

Your AI is fat.Feeding it is expensive.

Every conversation drags months of dead weight along, and when the memory lapses, the whole pile gets re-read at full price. sweap.it weighs your AI's memory, puts it on a diet, and keeps it off. Local-only. Reversible. Zero dependencies.

Last weigh-in2026-10-17
Before244.1 MB
Now206.5 MB
Dieted37.57 MB
Lost0 bytes
Pixel lifter Weigh it. Diet it. Keep it off.

The program

three lifts, run daily

01 / WEIGH

Step on the scale

sweap audits the agent's persistent store and shows exactly what each conversation costs: rows, megabytes, duplicated thinking blobs. You cannot diet what you do not weigh.

02 / DIET

Cut, don't burn

Duplicate thinking blobs get quarantined, not deleted. Every diet is reversible: restore the quarantine and the store comes back byte for byte.

03 / KEEP OFF

Watch the regrowth

A watcher samples the store every minute and flags when the weight creeps back. It flags, it does not prevent. The scale stays honest.

04 / PRICE

Know the bill

A lapse price turns megabytes into money at live model list prices: what a memory lapse costs when the whole pile gets re-read. Present tense, always.

Measured, not promised

one store · real rows · daily weigh-ins

finding  On the tested store schema, every thinking blob was stored twice,
         across all models tested: 9,456 rows, 26 MB.

weigh-in 2026-10-17   244.1 MB → 206.5 MB   dieted 37.57 MB
         bytes lost: 0 (quarantine = full undo)

watcher  sampling every minute · regrowth gets flagged
caveman makes your AI talk less · jev makes your AI think faster · gstack makes your AI a team ·sweap.it makes your AI weigh less.

Price board

what a lapse costs at list prices

Lapse price$0.49per MB, per lapse
5 MB lapse$2.06re-read at full price
20 MB lapse$8.23re-read at full price
50 MB lapse$20.58re-read at full price