About agentdb-query
agentdb-query is a skill for querying and managing AgentDB through a controller bridge. It is for users who need to store, retrieve, and search knowledge across agent sessions, with steps covering tiered memory, pattern search, context synthesis, and causal graphs.
Key features
- 01Tiered storage and recall
- 02Pattern storage and search
- 03Semantic routing and context synthesis
- 04Causal graph creation and queries
- 05Session lifecycle management
- 06Batch operations and feedback
Use cases
- 01Save and retrieve knowledge across agent sessions
- 02Search learned patterns
- 03Combine memories into synthesized context
- 04Check health and manage sessions
MCP support
The skill uses a controller bridge to call AgentDB's 20 MCP tools for health checks, memory operations, graph queries, and session management.
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ ruvnet/ ruflo --skill agentdb-queryAfter installing, type/agentdb-queryin Claude Code to confirm it loaded.
Details
From the project READMEAgentDB 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.
Steps
- Check health —
mcp__plugin_ruflo-core_ruflo__agentdb_health. Sanity-checkavailable: true. - Start session —
mcp__plugin_ruflo-core_ruflo__agentdb_session-startif not already active. - Store knowledge —
mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-storefor structured tier-keyed data (tiers:working|episodic|semantic). - Recall knowledge —
mcp__plugin_ruflo-core_ruflo__agentdb_hierarchical-recallwith a query. - Search patterns —
mcp__plugin_ruflo-core_ruflo__agentdb_pattern-searchfor learned patterns (ReasoningBank-routed). - Synthesize context —
mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesizeto combine multiple memories. - Build causal graph —
mcp__plugin_ruflo-core_ruflo__agentdb_causal-edgeto link related knowledge.
Available controller groups
Call mcp__plugin_ruflo-core_ruflo__agentdb_controllers to list the runtime registry. Functional categories surfaced via the 20 MCP tools:
- Hierarchical —
agentdb_hierarchical-store,_recall(tier-routed) - Pattern —
agentdb_pattern-store,_search(ReasoningBank-routed) - Semantic —
agentdb_semantic-route,_context-synthesize - Causal —
agentdb_causal-edge(graph-node backend with bridge fallback) - Lifecycle —
agentdb_health,_controllers,_session-start,_session-end - Bulk —
agentdb_batch(≤500 entries),_consolidate - Quality —
agentdb_feedback - Graph reads —
agentdb_graph-query(k-hop / semantic / pagerank from a domain-prefixed node id such asentity:xyz; SQL k-hop is bounded at 3 hops, checkappliedDepthandtruncated) andagentdb_graph-pathfinder - Deletes (destructive) —
agentdb_hierarchical-delete,agentdb_causal-edge-delete,agentdb_causal-node-delete. Confirm the exact ids with the user before calling; they are not undoable from this plugin.
Important: namespace handling
Namespace strings apply to memory_* and embeddings_search only. The agentdb_hierarchical-*, agentdb_pattern-*, and agentdb_causal-edge tools route by tier or controller, not namespace. Don't pass namespace: 'foo' to those tools — it will be silently ignored. See plugin README "Namespace convention".
Operational fallbacks (branch on these)
controller: 'memory-store-fallback'— pattern persisted viamemory_store --namespace pattern. NOT a failure._graphNodeBackend: true— causal-edge handled by@ruvector/graph-node.success: false, error: '...Use memory_store/memory_search instead.'— bridge unavailable; switch tomemory_*tools per the README replacement table.
CLI alternative
npx @claude-flow/cli@latest memory search --query "your query" --namespace patterns
npx @claude-flow/cli@latest memory store --key "key" --value "value" --namespace patterns
npx @claude-flow/cli@latest memory list --namespace patterns