// 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.
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.
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.
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.
| name | agentdb-causal-link |
| description | 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. |
Add a typed edge between two memories so future queries can traverse cause→effect, supersedes, depends-on, etc.
supersedes / amends / related-to between architecture decisionsagentdb_causal_edge(
fromMemoryId: <id>
fromMemoryType: 'episode' | 'pattern' | 'skill' | 'adr'
toMemoryId: <id>
toMemoryType: <same set>
relation: 'caused' | 'supersedes' | 'depends-on' | 'related-to' | <custom>
similarity?: 0..1
uplift?: -1..1 // signed reward delta
confidence?: 0..1
metadata?: { evidenceCount, sourceTimestamp, ... }
)
uplift is the secret sauce. Positive uplift = the causal link improved outcomes; negative = it hurt. The agentdb-investigator agent (this plugin) walks edges weighted by uplift × confidence to find root causes.
The agentdb 3.0.0-alpha.13 release added cascade: true semantics:
agentdb_causal_edge_delete(edgeId) — single edgeagentdb_causal_node_delete(nodeId, { cascade: true }) — node + all incident edges; returns deletedEdges countagentdb_edges_by_endpoints(from, to, label?) — bulk delete by tupleUse cascade when removing an obsolete ADR or decommissioning an agent — leaving dangling edges in the graph poisons future traversals.
agentdb_causal_explain quality.caused for correlation — reserve it for genuinely causal evidence (controlled change, repeated observation, expert confirmation).