simulated workspace — scripted world, real productsimulated demonew here? take the walkfor agents · connect your AI
architect

memory-health

embedding-worker telemetry. memory_units commit with embedding=NULL and the worker fills in vectors on a throttled cycle (default ~1 RPS, 5 rows per 30s). errored rows back off exponentially, capped at 10 minutes — a recovered dhara picks them up on the next cycle without intervention.

coverage

workspace-scoped. recall vector search only ranks embedded rows — non-embedded units fall back to tag/matter filtering.

total
33
live (non-deprecated) memory_units
embedded
0
rows with a vector
coverage
0.0%
embedded ÷ total
pending
33
embedding=NULL · 0 attempts
errored
0
embedding=NULL · attempts > 0
recent (24h)
0
successfully embedded in last 24h

per-matter embed progress

1 matter(s)
matterembeddedtotalcoverage
active-engagements0330.0%still embedding

worker

live · refreshed just now
state
stopped
enabled=true
last cycle
never run
last cycle counts
0 processed
0 ok · 0 failed
interval
30s
ARCHITECT_EMBEDDING_WORKER_INTERVAL_SECONDS
batch size
5
ARCHITECT_EMBEDDING_WORKER_BATCH_SIZE
rps
1
ARCHITECT_EMBEDDING_WORKER_RPS

errored sample

0 rows · oldest first

no errored rows. either the worker is hitting every embed cleanly or there are no live rows with embed_attempts > 0 right now.

gardener

daily pass: disabledlast fired neveryield: 0 suggestion(s) · 0 digest(s)
last-run report

no gardener checkpoint deposited yet — the daily pass deposits digests only on matters with findings, and only on Fridays.

D2 contradiction judge

the daily pass never judges — this is the human-triggered, supervised run. dry-run reads the band-candidate pool with zero LLM calls; judge run spends up to judgeCallCapPerRun BYOK calls and writes only judge-confirmed contradictions.

configusing stock defaults
admin role required to edit