hermes-mnemosyne
Hermes Mnemosyne Memory Provider
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMES_HOME/plugins/mnemosyne/.
Quick Reference
When comparing memory stacks for the user, use references/memory-tool-selection-mem0-vs-mnemosyne.md: Mnemosyne is preferred for Hermes local-first profile memory; Mem0 is the safer productized choice for external/customer-facing apps.
For migrations from overlapping stacks such as LCM + built-in memory + gBrain, use references/memory-stack-migration-pilot.md. Prefer a staged simplification: preserve LCM, pilot Mnemosyne as the external memory provider, keep the incumbent system read-only for rollback, and retire redundant writers after measured acceptance.
| What | How |
|---|---|
| Check if active | hermes memory status or check memory.provider in config.yaml |
| Memory stats | mnemosyne stats (CLI) or mnemosyne_stats (tool) |
| Manual consolidation | mnemosyne sleep (current session) or mnemosyne sleep --all-sessions |
| Dry-run consolidation | mnemosyne sleep --all-sessions --dry-run |
| Enable auto-consolidation | Set memory.auto_sleep: true + memory.sleep_threshold: 50 in config.yaml |
| Use Hermes' model for compression | MNEMOSYNE_HOST_LLM_ENABLED=true in .env |
| Check if installed | hermes memory status; if the symlink is missing, run ~/.hermes/hermes-agent/venv/bin/mnemosyne-install |