A controlled interface to AgentDB's memory and knowledge graph system, exposing 15 MCP tools through a standard workflow. You get hierarchical storage across working, episodic, and semantic tiers, pattern search routed through ReasoningBank, causal graph edges, and context synthesis. The skill walks through the typical path: health check, session start, store/recall, pattern search, and graph building. One thing to watch: namespace strings only apply to the raw memory tools, not the hierarchical or pattern controllers, which route by tier instead. If the bridge is unavailable, it falls back to basic memory_store and memory_search. Useful when you need cross-session knowledge persistence with more structure than flat key-value storage.
npx skills add https://github.com/ruvnet/ruflo --skill agentdb-query