skills.rest
ruvnet
ruvnetCOMMUNITY
Explore all skills by this author →
Website𝕏@ruvGitHub

agentdb-query

Query and manage AgentDB knowledge stores through MCP controller bridge tools.

70.1k|8.4k|Updated Jun 2, 2025
Search Tags:#AgentDB#Memory#pattern storage#MCP Tools#Semantic Search#Claude-Flow#Knowledge Graph
One-click install
npx skills add https://github.com/ruvnet/claude-flow --skill agentdb-query
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agentdb-query
Source: https://github.com/ruvnet/claude-flow/tree/main/plugins/ruflo-agentdb/skills/agentdb-query
Command: npx skills add https://github.com/ruvnet/claude-flow --skill agentdb-query

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AgentDB exposes 15 MCP tools across hierarchical storage, causal graphs, semantic routing, and pattern search, and this Skill provides the standard usage path so agents can store, recall, and synthesize knowledge across sessions without guessing tool order or namespace rules.

Core Features & Use Cases

  • Hierarchical Memory Operations: Store and recall tier-keyed data across working, episodic, and semantic tiers using agentdb_hierarchical-store and agentdb_hierarchical-recall.
  • Pattern and Causal Knowledge: Search ReasoningBank-routed patterns and build causal edges between related knowledge entries.
  • Context Synthesis and Lifecycle Management: Combine multiple memories with context-synthesize, and manage sessions, health checks, batch operations, and consolidation.
  • Use Case: An agent completing a multi-session coding task stores architectural decisions in the semantic tier, links them with causal edges, and recalls synthesized context at the start of the next session.

Quick Start

Ask the agent to check AgentDB health, start a session, and recall stored knowledge matching your query.

Frequently Asked Questions about agentdb-query

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I store and recall knowledge in AgentDB?▼

Use agentdb_hierarchical-store to save tier-keyed data into working, episodic, or semantic tiers, then retrieve it with agentdb_hierarchical-recall using a query. Start a session first with agentdb_session-start and verify availability with agentdb_health.

What MCP tools does AgentDB expose for memory management?▼

AgentDB exposes 15 MCP tools grouped into hierarchical storage, pattern store/search, semantic routing, causal edges, lifecycle management, batch operations, and feedback. Call agentdb_controllers to list the runtime registry.

Does the namespace parameter work with agentdb hierarchical tools?▼

No, namespace strings apply only to memory_* and embeddings_search tools. The agentdb_hierarchical-*, agentdb_pattern-*, and agentdb_causal-edge tools route by tier or controller, so a passed namespace is silently ignored.

What happens when the AgentDB bridge is unavailable?▼

The tools return success: false with an error directing you to use memory_store and memory_search instead. A controller value of memory-store-fallback means the pattern was persisted via memory_store and is not a failure.

Can I use AgentDB from the command line instead of MCP tools?▼

Yes, the claude-flow CLI provides memory search, store, and list commands via npx @claude-flow/cli@latest with a --namespace flag, offering an alternative path for pattern storage and retrieval.

Related Skills

Explore More Software Engineering Skills→
caura-aicaura-ai
420

memclaw

Store and recall long-term cross-session memories for multi-agent fleets.

Official
Advanced
Ic1558Ic1558

memory-manager

Consolidate AI memories using Python pattern detection and Git history.

Community
Advanced
sbussosbusso
189

add-qmd

Replace grep-based memory search with local QMD hybrid search.

Community
Intermediate
fzymgc-housefzymgc-house

address-findings

Apply code review fixes and manage dependencies in Git or Jujutsu repositories.

Official
Advanced