From agentdb-graph
Search and manage hyperedges — n-ary relationships between memories. Use for swarm membership, multi-cause incidents, or any "this involves all of (A, B, C, D)" relationship that doesn't fit a binary edge.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentdb-graph:agentdb-hyperedgeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Hyperedges connect more than two nodes — useful when a single relationship genuinely involves many participants.
Hyperedges connect more than two nodes — useful when a single relationship genuinely involves many participants.
agentdb_hyperedge_create(
nodes: [<id>, <id>, ...]
description: <one-liner>
embedding?: Float32Array
confidence?: 0..1
metadata?: { ... }
)
agentdb_hyperedge_search(
query: <semantic | nodeId>
topK?: 10
)
agentdb_hyperedge_delete(
id: <hyperedge id>
)
The agentdb_hyperedge_delete tool was added in agentdb 3.0.0-alpha.13.
Hyperedges are searchable by their description embedding — useful for "find all multi-agent collaborations on auth-related work" without enumerating every binary edge.
npx claudepluginhub ruvnet/agentdb --plugin agentdb-graphRecord a causal relationship between two memories in AgentDB — "X caused Y", "A supersedes B", "patch-foo depends-on patch-bar". Use when the user is documenting cause/effect, dependencies, supersessions, or after-action analysis.
K-hop traversal from a starting node in AgentDB's graph. Use to explore neighborhoods, find reachable nodes, or visualize a memory's "context".
Wires new concepts into a knowledge graph: searches for related entities, creates typed links (extends, depends_on, etc.), and checks minimum connection density.