crystal_recall
Recall crystallized (graduated, long-term) patterns relevant to a query — the on-demand semantic tier. Keyword scoring is corpus-aware (rare, distinctive terms outweigh common process-words, so recall stays precise on a large store), and recall also follows evidence edges — surfacing a pattern groun
How to use it
crystal_recall is exposed by the Anneal Memory MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the crystal_recall tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Anneal Memory
pip install anneal-memoryOther tools in Anneal Memory (8)
The always-on name + one-clause menu of the crystallized store — what graduated wisdom exists, so the agent isn't blind to its own corpus (the bodies fill on cue via crystalrecall)
Remove content that should not exist (PII, sensitive data). Cascades to associations. Logged in audit trail
At session end — returns episodes + current continuity + association context + compression instructions
Before making decisions that might have prior context. Query by time, type, keyword, or ID
When something important happens — a decision, observation, tension, question, outcome, or context change
After compressing — server validates structure, citations, records associations, applies decay, and saves
The prospective (spore) layer — open loops that must resolve, distinct from retrospective memory: sporeadd / sporelist / sporesurface / sporeget / sporeupdate / sporetouch / sporedescend / sporeascend. See Prospective memory — spores
Check memory health: episode counts, wrap history, continuity size, association network metrics