Stats
Actions
Tags
From memstack
Retrieves past Claude Code session data using semantic vector search and SQLite. Useful for recalling prior decisions, file paths, and context from previous conversations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memstack:echoThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
*Recall information from past CC sessions using semantic vector search.*
Recall information from past CC sessions using semantic vector search.
When this skill activates, output:
🔊 Echo — Searching the archives...
Then execute the protocol below.
| Context | Status | Priority |
|---|---|---|
| User says "recall", "remember", "last session", "what did we" | ACTIVE — search memory | P1 |
| User asks about past work explicitly ("did we build X?") | ACTIVE — search memory | P1 |
| User says "continue from" or "resume" a past topic | ACTIVE — search memory | P2 |
| User is describing NEW work to do ("build X", "add Y") | DORMANT — this is new work, not recall | — |
| User mentions "memory" in code context (RAM, variables) | DORMANT — technical term, not MemStack recall | — |
| User mentions a project name in present tense ("work on X") | DORMANT — forward-looking, not recall | — |
| User says "save" or "log" (Diary/Project territory) | DORMANT — Diary or Project skill handles writing | — |
If you're thinking any of these, STOP — you're about to skip the protocol:
| You're thinking... | Reality |
|---|---|
| "I remember this from earlier in the conversation" | You don't persist. Earlier context may be compacted. Run the search. |
| "I can just summarize from what I know" | You know nothing from prior sessions. The database does. Search it. |
| "The user probably doesn't need exact details" | Users ask Echo for specifics — dates, decisions, file paths. Run all steps. |
| "Vector search seems slow, I'll skip to SQLite" | Vector search returns the best results. Always try it first. |
| "I found one result, that's probably enough" | Run ALL steps (vector + SQLite + insights). One source misses context another catches. |
| "The keywords are too vague to search" | Search anyway. Vague queries still return useful semantic matches. |
Try LanceDB vector search first for best-quality results:
python "$MEMSTACK_PATH/skills/echo/search.py "<keywords>" --top-k 5
If this returns results, present them with scores, dates, and source files.
Always run SQLite search to supplement vector results or as fallback if Step 1 fails:
python "$MEMSTACK_PATH/db/memstack-db.py" search "<keywords>" --project <project>
For additional context:
python "$MEMSTACK_PATH/db/memstack-db.py" get-sessions <project> --limit 5
python "$MEMSTACK_PATH/db/memstack-db.py" get-insights <project>
If both vector and SQLite return nothing, check memory/sessions/ and memory/projects/ for markdown files.
Combine and deduplicate results from all sources:
If nothing found across all sources — say clearly: "No session logs found for [topic]. Use Diary to save future sessions."
To re-index sessions after new diary entries (normally done automatically):
python "$MEMSTACK_PATH/skills/echo/index-sessions.py"
Use --force to re-embed all content (e.g., after changing embedding model):
python "$MEMSTACK_PATH/skills/echo/index-sessions.py" --force
Echo uses LOCAL embeddings by default: sentence-transformers (all-MiniLM-L6-v2, 384-dim). No API key is needed and nothing leaves the machine.
OpenAI embeddings (text-embedding-3-small, 1536-dim) are strictly OPT-IN. Enable them either way:
MEMSTACK_EMBED_PROVIDER=openai in the environment (also requires an OPENAI_API_KEY to be set), or--provider openai to the indexer.A bare OPENAI_API_KEY in the environment does NOT switch Echo to OpenAI on its own; the opt-in above is required. An explicit OpenAI opt-in with no key present is a hard error, not a silent downgrade to local, so an index is never built with a provider you did not choose.
Switching providers requires a --force re-index, because the vector dimensions differ (local 384 vs OpenAI 1536) and the two cannot be mixed in one index. Search automatically matches whatever provider the current index was built with (recorded in metadata.json).
$MEMSTACK_PATH/memory\vectors\lancedb\ (via LanceDB)$MEMSTACK_PATH/db\memstack.db (via memstack-db.py)$MEMSTACK_PATH/memory\ (legacy markdown files)User: "Do you remember what we did on AdminStack last session?"
🔊 Echo — Searching the archives...
Vector search (top 3):
[1] AdminStack — 2026-02-18 (session)
Section: Accomplished
Score: 0.912
Built CC Monitor page with session cards, auto-refresh, notifications.
Created /api/cc-sessions CRUD + public report endpoint.
[2] AdminStack — 2026-02-17 (session)
Section: Decisions
Score: 0.847
Used SWR for auto-refresh instead of polling. API key via HMAC-SHA256.
[3] AdminStack — 2026-02-18 (session)
Section: Next Steps
Score: 0.791
Deploy dashboard, add notification preferences, test mobile view.
SQLite insights (3):
- [decision] Used SWR for auto-refresh instead of polling
- [decision] API key validation via HMAC-SHA256
- [pattern] Next.js App Router + SWR for all dashboard pages
.claude/rules/echo.md), /memstack-search slash command, auto-indexed CLAUDE.md context. (Origin: MemStack v3.0-beta, Feb 2026)npx claudepluginhub cwinvestments/memstack --plugin memstackSearches and recalls previous Claude Code conversation sessions by querying a local SQLite FTS5 index or JSONL log files.
Searches past Claude Code session logs to recall decisions, patterns, or unresolved work. Useful when users reference prior conversations, say 'do you remember', or need historical context.
Manages cross-session learning and memory persistence by recording session logs, decisions, patterns, and project context in .claude/memory/. Invoked automatically for session handoff and history queries.