From agentdb-causal
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.
npx claudepluginhub ruvnet/agentdb --plugin agentdb-causalThis skill uses the workspace's default tool permissions.
Three-tier memory matching how humans actually use memory. Each tier has different retention, retrieval cost, and query semantics.
Explains agent memory architectures: short-term context window, long-term vector stores, CoALA cognitive types (semantic/episodic/procedural). Recommends frameworks like LangMem/MemGPT and stores like Pinecone/Qdrant.
Implements unified four-tier memory system for AI agents: Tier 1 semantic search (Serena+Forgetful), Tier 2 episodic session replay, Tier 3 causal graphs. Use for memory-first checks before code changes.
Manages four-tier memory for AI agents: Tier 1 semantic search (Serena+Forgetful), Tier 2 episodic session replay, Tier 3 causal graphs. Enables memory-first checks before code changes per Chesterton's Fence.
Share bugs, ideas, or general feedback.
Three-tier memory matching how humans actually use memory. Each tier has different retention, retrieval cost, and query semantics.
| Tier | Retention | Use for |
|---|---|---|
| working | minutes (auto-expires) | The current task's scratch — files open, hypotheses, in-flight decisions |
| short | hours-days | Recent session context — what was decided this morning |
| long | indefinite (until pruned) | Cross-session facts, patterns, lessons |
agentdb_hierarchical_store(
key: <namespace key> // e.g. 'task:auth-refactor:hypothesis'
tier: 'working' | 'short' | 'long'
value: <stringified content>
ttl?: <seconds> // overrides tier default
metadata?: { topic, project, ... }
)
agentdb_hierarchical_recall(
query: <semantic or exact key>
tier?: <filter> // omit to search all tiers
k?: 5
)
agentdb_hierarchical_delete(
key: <namespace key>
tier?: <filter>
)
The delete tool was added in agentdb 3.0.0-alpha.13. Before that, there was no first-class way to remove an entry — re-indexing workflows like ruflo's /adr-index couldn't purge stale ADRs. Now they can.
working first — it's smallest, freshest, highest signal for "what am I doing right now."short if working returns nothing.long last for established knowledge.tier=undefined and let the bandit weight by tier × similarity.working — they expire and you lose them.long — it pollutes searches forever.