engram_storeStore a memory. All memories start in Buffer and promote to Working/Core through
engram_recallHybrid semantic + keyword search with budget-aware retrieval.
engram_recentList recent memories by creation time. Good for session context recovery.
engram_resumeFull memory bootstrap for session recovery. Returns core (permanent knowledge),
engram_extractExtract structured memories from raw text using LLM.
engram_searchQuick keyword search. Lighter than recall — no scoring or budget logic.
engram_consolidateRun a memory consolidation cycle. Promotes important memories upward,
engram_statsGet memory statistics: counts per layer, AI status, version.
engram_repairRepair FTS search index. Removes orphaned entries and rebuilds missing ones.
engram_healthDetailed health check: uptime, RSS memory, embed cache stats, AI config status.
engram_triggersFetch trigger memories for a specific action. Call before performing an action (e.g. git-push, deploy) to recall relevant lessons and rules.
engram_deleteDelete a memory by ID. Use when a memory is outdated, incorrect, or redundant.
engram_updateUpdate a memory
engram_trashList soft-deleted memories. Recently deleted items can be restored.
engram_restoreRestore a soft-deleted memory from trash back to its original layer.
engram_topicDrill into topic clusters by ID. Use after /resume to explore specific topics from the knowledge index.
We re-grade npm:engram-rs-mcp on a schedule and alert your Slack/webhook the moment its tools change or its grade drops — rug-pull insurance for the connection.
Add the wmcp.sh trust oracle as an MCP server and call grade_mcp_server / check_mcp_drift in your agent's pre-connection gate:
https://wmcp.sh/mcp/trust
readOnly vs observed behavior) layer on via the wmcp.sh proxy.