Module graph 

recall-graph — Knowledge graph with semantic search for AI memory systems.

Provides a structured graph layer (Layer 0) underneath flat-file memory systems. Used by recall-echo (pulse-null entities) and recall-claude (Claude Code users).

Re-exports

pub use confidence::Provenance;

pub use confidence::ProvenanceWeights;

pub use ingest::IngestContext;

pub use ingest::ProvenancePolicy;

pub use store::ServerConfig;

Modules

confidence

Bayesian confidence model for relationship edges.

crud

Entity and relationship CRUD operations.

dedup

LLM-powered entity deduplication — skip, create, or merge decisions.

embed

Text embedding via fastembed (BGE-Small-EN-v1.5, 384 dimensions).

error

Typed error handling for recall-graph.

extract

Conversation chunking and LLM-powered entity/relationship extraction.

gc

Garbage collection for the knowledge graph.

ingest

Ingestion orchestrator — chunk → episode → extract → dedup → relationships.

llm

Minimal LLM provider trait for knowledge graph operations.

pipeline

Pipeline document parser — converts praxis pipeline markdown documents into graph entities.

pipeline_sync

Pipeline sync engine — reconcile flat-file pipeline state with the graph.

query

Hybrid query — combines semantic search, graph expansion, and episode search.

search

Semantic search across entities and episodes using HNSW KNN + hotness scoring.

store

SurrealDB store — embedded (kv-surrealkv) or server (WebSocket), selected at runtime via the [graph] mode config key (embedded | server).

traverse

Graph traversal — recursive depth-first with cycle detection.

types

util

Shared utility functions for the graph subsystem.

utility

Outcome feedback loop for adaptive entity learning.

vigil_sync

Vigil-pulse sync engine — ingest metacognitive signals and outcomes into the graph.

Structs

GraphMemory

The main entry point for graph memory operations.