--- title: Mnemosyne type: system status: active created: 2026-07-22 updated: 2026-10-01 verified_on: 2026-10-01 confidence: high tags: [memory, mnemosyne, backend] sources: [live-probe, mnemosyne-db, config, ops-profile-config] --- # Mnemosyne ## Purpose Primary agent memory store for Hermes. ## Current Configuration - **Provider:** `mnemosyne` - **Enabled:** true - **Auto sleep:** true - **Default scope:** `session` - **Memory char limit:** 5000 - **User char limit:** 3000 - **Vector type:** int8 - **Profile isolation:** true - **Shared surface read:** true - **Shared surface path:** `data/shared/mnemosyne.db` - **Skip contexts:** cron, flush, subagent, background, skill_loop - **Reflect max calls per session:** 3 - **Sync roles:** user - **Flush every:** 6 turns - **Embedding model:** `BAAI/bge-small-en-v1.5` (384 dims) - **Embeddings via API:** false (local fastembed) ## Database Stats (2026-08-02) | Table | Rows | Notes | |---|---|---| | `working_memory` | 1,476 | Active memories | | `episodic_memory` | 458 | Consolidated summaries | | `memory_embeddings` | 158 | Only working memories — **0 episodic** | | `memory` (legacy) | 2,181 | Old table, not migrated | | `vec_working` | 159 | Vector index rows | | Shared surface | 0 | Empty — cross-agent sharing not functional | ## Known Issues ### Vector embedding coverage gap - **Only 159/1,476 working memories (10.8%)** have vector embeddings - **0/458 episodic memories** have embeddings - Semantic search (`mnemosyne_recall`) falls back to FTS5 keyword matching for ~90% of working and 100% of episodic memories - This means recall quality is degraded — vector similarity can only search a tiny fraction of the memory store - **Root cause:** The embedding pipeline (fastembed) never processed the bulk of memories. The `vec_working` table was rebuilt once (Jul 18) but only captured 159 rows. - **Fix needed:** Backfill embeddings for all working and episodic memories. This requires running the embedding pipeline across the full dataset. ### Profile isolation chosen over shared surface |- The ops profile was enabled with mnemosyne on 2026-08-02 |- **Decision:** `profile_isolation: true` was set on ops, giving each profile its own independent memory bank — zero cross-contamination |- `data/shared/mnemosyne.db` exists with 0 rows; cross-profile sharing is intentionally unused |- This means Tusk (ops) and Rhino (default) do not share memories, which is the desired behaviour |- Config in `~/.hermes/profiles/ops/config.yaml`: `memory.mnemosyne.profile_isolation: true`, `allow_tool_override: false`, `shared_surface_read: false` |- Verified end-to-end on 2026-08-02: memory writes land correctly in both profiles independently ### Legacy table not migrated - 2,181 rows in the old `memory` table are not in the new `working_memory`/`episodic_memory` system - These are only accessible via the legacy `memory` tool, not via `mnemosyne_recall` ### Gateway notifications were captured as user memories (fixed 2026-09-30) - Hermes's background-process notifications (long-running `terminal` jobs reporting completion) were being written into Mnemosyne as **`[USER] [Anthony Martin]`** memories — i.e. machine messages were stored as if the user had said them, and then surfaced during recall as if they were his words. - **36 such rows** were found and purged on 2026-09-30 (working tier plus the corresponding episodic rows). Recall after the purge returned clean. - Two **canonical facts** were also wrong because of the same class of drift: `hermes_cron_model_default` named the removed provider `custom:omni` instead of `custom:omni-101`, and the Daily Marketing Job Radar's model fact was stale. Both corrected. - **Rule:** treat a recalled memory attributed to a person as untrusted until the attribution makes sense in context. Machine-generated status text should never enter the person-attributed tier. ## Known Management Jobs - Mnemosyne Auto-Consolidate every 30m — script: `consolidate_mnemosyne.sh`, mode: no-agent - Mnemosyne DB Backup weekly Sunday 03:00 — script: `mnemosyne-backup.sh`, mode: no-agent - Mnemosyne Health Monitor every 12h — skill: `mnemosyne-operations`, reports only on exception - Mnemosyne Watchdog every 15m — script: `mnemosyne-watchdog.py`, mode: no-agent ## History and Evidence - **2026-09-30 memory-hygiene pass:** 36 gateway-notification rows purged from the person-attributed tier; two canonical facts corrected (`hermes_cron_model_default` → `custom:omni-101`, job-radar model). No unresolved conflicts left in the working tier. - **2026-08-19 Mnemosyne Watchdog incident:** Watchdog job (`96eb95ce12f2`) cycled for ~2 hours early morning Aug 19 reporting no consolidation for 36–41.5+ hours (last consolidation Aug 17 07:15). Watchdog stopped after ~2 hours of alerts. See [[systems/scheduled-tasks]] Known Issues section. - **2026-08-18 incident:** Working memory capture (`sync_turn`) stopped functioning after 2026-08-16 23:15:39 — ~48 hours of conversation turns not captured. Root cause: silent guard conditions in `run_agent.py:_sync_external_memory_for_turn()`. Config is clean (native YAML types). MEMDEBUG logging recommended to identify which guard blocks. See [[incidents/2026-08-18-mnemosyne-capture-pipeline]]. - **2026-08-01 incident:** Automatic conversational capture was broken by stringified structured YAML, especially `sync_roles: "['user']"`. Fixed by rewriting with native YAML types. See [[incidents/2026-08-01-mnemosyne-capture-failure]]. - **2026-08-01 cleanup:** Legacy always-injected memory reduced from 8,013 bytes to 4,998 bytes (memory) and 2,958 bytes (user). - **2026-07-29 incident:** `memory.mnemosyne.tools: None` caused schema loading warnings. Fixed by removing the line. See [[incidents/2026-07-29-mnemosyne-relay]]. - **2026-07-29 relay scope corruption:** `RuntimeError: scope handle is not at the top of the stack` — 3 occurrences, self-resolved. ## Related - [[concepts/agent-memory]] - [[comparisons/memory-backends]] - [[incidents/2026-08-01-mnemosyne-capture-failure]] - [[incidents/2026-08-18-mnemosyne-capture-pipeline]] - [[incidents/2026-07-29-mnemosyne-relay]]