Save a new memory node with dense vector embedding, category, importance, project namespace, and conflict detection.

Search memory using 4-Way Reciprocal Rank Fusion (RRF): Fuses Dense Vector Cosine Similarity + Trigram FTS5 Lexical + Graph Spreading Activation + ACT-R Decay.

Autonomous Memory Extractor Agent: Deconstructs text into atomic facts, extracts entity triples for the knowledge graph using hybrid local LLM sidecar + expanded NLP regex heuristics, and indexes vectors.

Save a Subject-Predicate-Object relation with bi-temporal validity and project namespace.

Query knowledge graph relations with recursive multi-hop path traversal and bi-temporal filtering.

Autonomous Memory Deduplication & Semantic Merging Agent: Finds clusters of duplicate/near-identical memory nodes, merges access counts and edges, and prunes redundant duplicate records in chunks of 1,000 nodes.

Knowledge Graph Topology Visualizer: Generates Mermaid.js and ASCII relational network diagrams for power users.

Autonomous Memory Reflector Agent (Episodic Reflection): Synthesizes low-level episodic nodes into durable high-level insights.

Ingest an entire Obsidian markdown vault into the knowledge graph and vector store.

Execute WAL flush, vacuum, and performance optimization.

Auto-Context Boot Tool for Agents: Recalls top high-importance active memories formatted in XML for session initialization.

Edit an existing memory's content, importance, or category by its node ID.

Delete a memory node and cascade-delete all its associated knowledge graph edges by ID.

List recent memory nodes in the database, ordered by importance and recency.

Get system statistics, knowledge graph counts, and active hardware acceleration tier.