// K-hop traversal from a starting node in AgentDB's graph. Use to explore neighborhoods, find reachable nodes, or visualize a memory's "context".
| name | agentdb-traverse |
| description | K-hop traversal from a starting node in AgentDB's graph. Use to explore neighborhoods, find reachable nodes, or visualize a memory's "context". |
Walk outward from a node up to K hops, returning the visited subgraph.
agentdb_kHopNeighbors(
startId: <node id>
k: 1..5 // hops
edgeFilter?: [<relation>, ...] // limit to specific relations
direction?: 'in' | 'out' | 'both'
maxNodes?: 100 // safety cap
)
Returns: { nodes, edges, stats: { reachable, capped } }
| Goal | Pattern |
|---|---|
| Forward influence | direction: 'out', k: 3 |
| Backward dependencies | direction: 'in', k: 3 |
| Local neighborhood | direction: 'both', k: 1 |
| Causal chain only | edgeFilter: ['caused', 'supersedes'] |
| Skill composition graph | edgeFilter: ['composes', 'requires'], start: skill id |
K-hop fans out exponentially. With average degree d, k hops returns up to d^k nodes. AgentDB defaults maxNodes: 100 — when you hit the cap, stats.capped: true and you should rerun with smaller k or tighter edgeFilter.
k > 4 without edgeFilter — explosive fan-out destroys the answer's signal.Walk the causal graph in AgentDB to explain why two memories are connected, or trace a root cause. Use when the user asks "why did X happen", "what led to Y", or after an incident.
Record 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.
Store memories in tier-aware hierarchical memory — working / short-term / long-term — and recall with tier filters. Use for working-set context that should fade, vs facts that should persist, vs patterns that should be searchable forever.
Initialize an AgentDB Cognitive Container (.rvf file) in the current project. Sets up storage, embedder config, and the agentdb MCP server. Use when the user is starting a new project that needs vector memory, or asks to "set up agentdb" / "init agentdb".
Show AgentDB health — pattern count, embedder status, cache hit rate, learning gain since init. Use when the user asks "is agentdb working?", "how many memories?", "show agentdb stats", or after long-running sessions to confirm state.
Execute Cypher queries against AgentDB's graph backend. Use when the user wants to write a custom traversal that the standard tools don't cover, or when explaining graph state.