remember
Store a fact, preference, or piece of context. Optional kind classification (fact, decision, question, preference, or custom) and importance weighting. Reports overlapping observations so the AI can consolidate incrementally. Returns versionhash for cache invalidation.
How to use it
remember is exposed by the Hippocampus MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the remember tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Hippocampus
claude mcp add hippocampus --transport http http://localhost:3000/mcpOther tools in Hippocampus (10)
"Did anything change?" — pass an entity name + cached hash, get back yes/no. No embedding computation, pure metadata.
Find clusters of similar/duplicate memories, detect near-duplicate entities, surface contradictions, or run sleep mode for batch lifecycle analysis (compress/prune/refresh)
Get everything about a topic — observations, relationships, related entities. Includes versionhash.
Export as CLAUDE.md context file, readable markdown, JSON, wire format, or Obsidian vault
Permanently delete a memory or entity (secure deletion)
Merge multiple observations into one (atomic consolidation). Returns versionhash.
Merge multiple entities into one — moves all data, deletes sources. Returns versionhash.
Bootstrap memory from a new AI session. Returns structured extraction instructions the AI follows to capture user context.
Search memories by semantic similarity + keyword match. Filter by type, kind, since. Use spread: true to follow relationships and discover connected memories. Includes versionhash per entity in all formats.
Replace an existing observation with new content. Returns versionhash.