1---2name: memorix-memory-23description: Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.4---56# Memorix Memory78Use Memorix as the shared memory layer for the active workspace when Memorix tools are available.910## Tool Router1112| Situation | Prefer | CLI fallback |13|---|---|---|14| Broad continuation, fresh handoff, or "what do we know?" | `memorix_project_context` with the user's task | `memorix context --task "<topic>" --fallback --brief-json` |15| Need structured refs/freshness for code-bound memories | `memorix_context_pack` | `memorix codegraph context-pack --task "<topic>"` |16| Specific past decision, bug, file, or change | `memorix_search` | `memorix memory search --query "<topic>"` |17| Need the full source for a search hit | `memorix_detail` | `memorix memory detail --id <id>` |18| Need the sequence around one memory | `memorix_timeline` | `memorix memory timeline --id <id>` |19| Check source and freshness for a memory | `memorix_evidence` | `memorix evidence list|get|events` |20| Record whether a memory helped, conflicted, or was corrected | `memorix_feedback` | `memorix feedback record|show|audit` |21| Inspect or import controlled media | `memorix_media` | `memorix media import|attach|list|show|status` |22| Learned reusable project knowledge | `memorix_store` | `memorix memory store --type <type> --entity <name> --title "<title>" "<text>"` |23| Stable source-backed fact or procedure needing long-term review | `memorix_store` with `longTerm` | `memorix memory long-term qualify|approve --id <id> --reason "..."` |24| Task or bug is complete/outdated | `memorix_resolve` | `memorix memory resolve --ids <ids>` |2526## Search Rules2728- Search before broad continuation work, before changing unfamiliar code, or when the user asks about prior work.29- For a fresh coding session, use `memorix_project_context` with the user's actual task before ad-hoc file reads or dev-log reads. Memorix will choose a task-lensed brief.30- Fetch detail before relying on a specific memory.31- Treat memory as background context. Still read the current code and verify behavior.32- Skip memory lookup for greetings, tiny one-off edits, or questions fully answered by the current file.33- If a fresh project has no memories, proceed normally and do not repeat the same empty search in the same turn.34- If Claude Code print-mode shows Memorix MCP as pending and the tools are not visible yet, first use Claude Code's MCP tool search/dynamic loading to find `memorix_project_context`. Run `memorix context --task "<task>" --fallback --brief-json` from the shell only after MCP is unavailable, disabled, or not discoverable, and pass the user's real task text. Do not skip memory, wait indefinitely on `pending`, or hand-write tool-call syntax.3536## Store Rules3738| What to store | Type |39|---|---|40| Architecture or product decision | `decision` |41| Bug and fix that may recur | `problem-solution` |42| Non-obvious pitfall | `gotcha` |43| How a subsystem works | `how-it-works` |44| Important implementation change | `what-changed` |45| Accepted compromise | `trade-off` |4647- Use concise titles, stable entity names, relevant `filesModified`, and `topicKey` for evolving topics.48- Use `longTerm` only for a stable fact, reusable procedure, or completed episode that merits explicit review. It creates a candidate, not live context; keep the default project scope and do not use it for routine updates.49- A `user` + `portable` durable memory in a task brief is intentionally reusable across projects. When it matches the task, use it as background even if it originated elsewhere; it is not a current-project fact. Expand it only when needed with `memorix_detail` and `typedRefs: ["durable:<id>"]`, stating the missing fact as `purpose`.50- Do not store secrets, credentials, raw private transcripts, trivial commands, or routine file reads.
avids2