Crate mentedb 

MenteDB: The Mind Database for AI Agents

MenteDB is a purpose-built database engine for AI agent memory. It’s a cognition preparation engine that pre-digests knowledge for single-pass transformer consumption.

Core Concepts

• MemoryNode: The atomic unit of knowledge (embeddings, graph, temporal, attributes)
• MemoryEdge: Typed, weighted relationships between memories
• MemoryTier: Cognitive inspired storage hierarchy (working, episodic, semantic, procedural, archival)
• Context Assembly: Token budget aware context building that respects attention patterns
• MQL: Mente Query Language for memory retrieval and manipulation

Quick Start

use mentedb::prelude::*;
use mentedb::MenteDb;
use std::path::Path;

let mut db = MenteDb::open(Path::new("./my-agent-memory")).unwrap();
// store, recall, relate, forget...
db.close().unwrap();

Feature Highlights

• Unified process_turn pipeline: single call handles context retrieval, pain signals, episodic storage, write inference, action detection, sentiment, phantom tracking, trajectory, speculative caching, fact extraction, and auto-maintenance (decay / archival / consolidation)
• Seven cognitive features: interference detection, pain signals, phantom tracking, speculative caching, stream monitoring, trajectory tracking, write inference
• HNSW vector index with hybrid search (vector + tags + temporal + salience)
• CSR/CSC knowledge graph with belief propagation
• Token budget aware context assembly with attention curve optimization
• MQL query language with vector, tag, temporal, and graph traversal support
• WAL based crash recovery with LZ4 compressed pages

Repository

Source code: https://github.com/nambok/mentedb

Re-exports

pub use mentedb_cognitive as cognitive;

pub use mentedb_consolidation as consolidation;

pub use mentedb_context as context;

pub use mentedb_core as core;

pub use mentedb_graph as graph;

pub use mentedb_index as index;

pub use mentedb_query as query;

pub use mentedb_storage as storage;

Modules

enrichment

Sleeptime enrichment pipeline (requires enrichment feature). Sleeptime enrichment pipeline orchestrator.

prelude

Commonly used types, re-exported for convenience.

process_turn

Unified process_turn orchestration. Unified process_turn orchestration.

Structs

CognitiveConfig

Configuration for the cognitive engine subsystems.

EnrichmentConfig

Configuration for sleeptime enrichment pipeline.

EnrichmentResult

Result of running the enrichment pipeline.

EntityLinkResolution

A confirmed entity resolution from an external resolver (LLM).

EntityLinkResult

Result of a single entity linking run.

EntitySeparation

A pair of entity names that the LLM confirmed are DIFFERENT entities.

MenteDb

The unified database facade for MenteDB.

Constants

VERSION

Engine version, derived from Cargo.toml at compile time.