Search past decisions, procedures, learnings, or context relevant to the current task. Trigger when work connects to prior decisions, a debugging pattern resembles a past issue, the user asks about rationale, or uses recall language like "that approach" or "like before".
Find what the user already knows. Search their memories and past conversations for decisions, procedures, and context that make the current task sharper.
For continuation-style engineering work, search near the start of the task. Do not wait for the user to literally say "search memory".
Strong signals (search when):
Contextual signals (consider searching when):
When NOT to search:
nmem --json m search "query" for durable knowledge (decisions, insights, procedures).nmem --json t search "query" --limit 5 when the user is asking about a prior conversation or exact session history.source_thread, inspect it progressively with nmem --json t show <thread_id> --limit 8 --offset 0 --content-limit 1200.If the runtime already knows the active project or agent lane, add --space "<space name>" to these commands.
If results are weak or the need is conceptual/historical, try deeper matching:
nmem --json m search "query" --mode deep
Add filters only when the task clearly implies them:
-l "label-name"--importance 0.7--event-from 2026-01-01 / --event-to 2026-03-01-s codex-n 10Summarize only the strongest matches and clearly say when nothing relevant was found.