Agentdb Query

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.

skills.sh installs: 746
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill agentdb-query --agent claude-code

Installs into .claude/skills of the current project.

Files

AgentDB Query

Query and manage AgentDB through the controller bridge. AgentDB exposes 20 agentdb_* MCP tools; this skill enumerates the standard usage path.

When to use

When you need to store, retrieve, or search knowledge across agent sessions. AgentDB provides hierarchical storage, causal knowledge graphs, semantic routing, and context synthesis.