M
Mnemosyne
v2.8.0 — Tiered Memory & Confidence

Memory for AI Agents
That Actually Works

Mnemosyne is a native memory system for AI agents. Persistent, structured, and context-aware — built on SQLite with vector search, full-text retrieval, and biological-inspired BEAM architecture.

Why Mnemosyne?

BEAM Architecture

Biological-inspired memory tiers: Working, Episodic, Semantic, and Scratchpad — each optimized for different access patterns.

Hybrid Retrieval

Combine dense vector similarity with SQLite FTS5 full-text search for results that are both relevant and precise.

SQLite Native

Zero external dependencies. Single-file database with ACID transactions, portability, and proven reliability.

Privacy First

All data stays local. Optional encryption at rest. No cloud required, no data exfiltration.

Sub-100ms Queries

Optimized indexing and caching deliver median retrieval latency under 100ms for typical workloads.

Hermes Integration

First-class plugin for the Hermes agent framework. Auto-context injection, tool schema, and seamless operation.

<100ms
Median Query
4
Memory Tiers
0
External Deps
Scale Potential

Ready to give your agent a memory?

Start with the Quick Start guide and have Mnemosyne running in under 5 minutes.

Quick Start