20 KiB
title, type, status, created, updated, verified_on, review_after, confidence, tags, sources
| title | type | status | created | updated | verified_on | review_after | confidence | tags | sources | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Mnemosyne | system | active | 2026-07-22 | 2026-11-09 | 2026-11-09 | 2026-11-13 | high |
|
|
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 (live, 2026-10-04)
| Table | Rows | Notes |
|---|---|---|
working_memory |
773 | Active memories |
episodic_memory |
1,047 | Consolidated summaries |
memory_embeddings |
760 | Working-tier embeddings |
memory (legacy) |
2,181 | Old table, not migrated |
vec_working / vec_working_rowids |
760 | Working vector index |
vec_episodes / vec_episodes_rowids |
1,035 | Episodic vector index |
vec_facts_rowids |
0 | memoria_facts is intentionally left unvectorised |
| Shared surface | 0 | Empty — cross-agent sharing not functional |
Embedding coverage (live, 2026-10-04): 1,759/2,194 memories embedded (80.2%) — working 726/752 (96.5%), episodic 1,033/1,039 (99.4%); 13 embeddings generated in the previous 24h. Working coverage is above the 95% alert threshold enforced by the Embedding Coverage job (b63ed5817212, every 6h, Telegram topic 102).
Known Issues
⚠ Security - live .env values are stored verbatim in this store's own tables (live read 2026-11-06 00:2x-00:5x AWST). 17 rows carry three live credentials - TELEGRAM_BOT_TOKEN (4 rows), MATTERMOST_TOKEN (6) and HERMES_CUSTOM_OMNIROUTE_20128_API_KEY (7) - across memories.content, working_memory.content, episodic_memory.content, gists.text, memoria_facts.context_snippet and the fts_episodes / fts_working mirrors (per-key breakdown on the incident page). The 0-byte episodic_memory.db and memoria_facts.db stubs beside mnemosyne.db hold nothing - those names are tables inside the main DB. Capture stores verbatim session text (the 1.7 GB session store state.db itself carries all four values), so any session in which a key was printed becomes recall material. Recall is the exposure path: these rows can be pulled into any prompt, cron delivery or subagent transcript, and Mnemosyne's own rotation snapshots (seven uncompressed .db files under backups/) reproduce the whole DB. Not remediated. -> incidents/2026-11-05-secrets-at-rest-in-mnemosyne-and-cron-prompts. Capture-time redaction of .env values is the durable fix; rotation is the only remedy that also covers the existing copies.
Tier counts + pipeline status (live, 2026-10-18 12:1x — health job ea79a2107e36, exited 1): DB 27 MB; working 801, episodic 1,065; embeddings working 775/801 (96.8 %), episodic 1,059/1,065 (99.4 %) — both above the 95 % floor, no reindex needed. FTS5 aligned on all three indexes (fts_working / fts_episodes / fts_facts); consolidation ran 2026-10-18 03:55 (0 items — nothing new to consolidate); 1 unresolved conflict (benign, threshold 10); Mnemosyne provider registered, 40 tools; watchdog exit 0. The job's red was a capture-staleness false positive: working_memory had no non-cron row since 2026-10-16 11:07 simply because no user conversation had occurred — the gateway restarted 2026-10-17 05:10, Telegram reconnected 10:45, and capture was idle rather than broken. The 24 h threshold in ~/.hermes/scripts/mnemosyne-health-check.sh:92 will keep flagging idle weekends; expect repeat reds until it gains a "no recent conversations" guard or the threshold is raised. Same trap class as the naive-UTC clock note below.
Tier counts (live, 2026-10-09 22:27): working 773, episodic 1,047, canonical_facts 97, facts 871, memoria_facts 407, memoria_preferences 132, conflicts 152 (1 open — id 152, contradiction, created 2026-10-09 13:11:38), working embeddings 760/773, episodic embeddings 1,043/1,047 (99.6%). Ranking relevance is the live issue, not coverage — see incidents/2026-10-09-memory-recall-relevance.
Tier counts (live, 2026-11-01 03:0x — the 2026-10-09 ranking incident is now RESOLVED): working 941, episodic 1,124, canonical_facts 90, conflicts 175 (11 open — ids 165–175, all contradiction, all created in one batch at 2026-10-31 19:26:39 and sharing a single fact_a_id, the extraction-noise signature), working embeddings 927/941 (98.5%), episodic embeddings 1,124/1,124 (100%) — both tiers above the 95% floor, no reindex needed. The recall weights are live in ~/.hermes/mnemosyne/config.yaml (vec_weight: 0.5, fts_weight: 0.3, importance_weight: 0.3, plus MNEMOSYNE_IMPORTANCE_WEIGHT=0.3 in the environment) — not in ~/.hermes/config.yaml's memory.mnemosyne block, which is why the 2026-10-10 probe wrongly concluded the fix was never applied. The original regression query now returns only substantive current-state facts; the stale Uber Eats episode no longer outranks them → incidents/2026-10-09-memory-recall-relevance (resolved).
Tier counts (live, 2026-10-12 12:02 — health job ea79a2107e36, green): working 760/786 embedded (96.7%), episodic 1050/1056 (99.4%) — both above the 95% floor, no reindex needed (b63ed5817212 continues to backfill). Orphan embeddings 0. FTS5 exactly aligned: fts_working 786/786, fts_episodes 1056/1056, fts_facts 876/876. 0 unconsolidated working rows; 1 unresolved conflict (threshold 10); last consolidation 0.3 h earlier; 2,252 memories total (786 working / 1,056 episodic / 1 triple); disk 15 GB free (81% used). Interpretation: coverage is not the live issue — ranking relevance is (see incidents/2026-10-09-memory-recall-relevance).
Tier counts (live, 2026-10-12 00:1x): working 786, episodic 1,056, facts 876 (fts_facts 876 — FTS aligned), fts_working 786, memoria_facts 410, conflicts 152. Embeddings: working 773/786 (98.3%), episodic 1,052/1,056 (99.6%) — both above the 95% reindex threshold; the coverage job b63ed5817212 backfilled 15 vectors since the 2026-10-11 00:08 check.
Capture clock is naive UTC — never compare it to AWST now (2026-10-11 false alarm). At 2026-10-11 00:08 the health monitor raised an EXCEPTION claiming the capture path had stalled for 10.7 hours, citing working_memory MAX(created_at) = 2026-10-10 13:24:53 against the local clock. created_at is stored as a naive UTC string (the same trap as consolidation_log), so the real gap was 2.7 h: that write landed at 21:24:53 AWST, inside the 21:13 session that produced it. Capture was healthy throughout — working_memory gained 2 rows on 2026-10-11 (11:19:37 and 11:51:39 UTC = 19:19 / 19:51 AWST), both from the day's only interactive session. Convert to local before judging staleness; a raw MAX-vs-now comparison always looks ~8 h stale in AWST.
Vector embedding coverage gap — RESOLVED (2026-08-02)
- Was: only 159/1,476 working memories (10.8%) embedded and 0 episodic, so recall fell back to FTS5 for ~90% of working and all episodic memories.
- Resolved by the 2026-08-02 reindex pass. Live coverage on 2026-10-04 is 96.5% working / 99.4% episodic, and new embeddings are still being generated. The figures above are kept as the before-state only.
- Standard repair if coverage drops below 95% working:
~/.hermes/hermes-agent/venv/bin/mnemosyne reindex --yes(the Embedding Coverage jobb63ed5817212triggers the same path every 6h).
Vector recall silently ran FTS-only (2026-10-03 — repaired)
fastembedwas absent from every uv-managed runtime, so the dense leg ofmnemosyne_recallproduced no candidates and recall fell back to FTS5/keyword scoring without raising an error. Sessions kept working, which is why it went unnoticed.- Compounded by
FASTEMBED_CACHE_PATHbeing unset in~/.hermes/.env, and by the embedding worker sometimes launching in isolated (python -I) mode, which does not inheritPYTHONPATH. - Repaired 2026-10-03:
fastembedinstalled into the bootstrap-selected runtime,FASTEMBED_CACHE_PATHpinned, andhermes-runtime-deps-guard.shextended to assert fastembed + cache path + model dir every 15 min alongside its existingdotenv/mnemosynechecks. - CLI caveat — do not misread
mnemosyne doctor. Doctor and the recall CLI run under the legacyvenv/(Python 3.11), where thesqlite_vecextension is not importable; doctor therefore printsvec0: present_but_unloadableand marks the vector tiersunavailableeven while the gateway embeds normally. Judge vector health with~/.hermes/scripts/check_embedding_coverage.py, not with doctor'svec0line. - Benign noise:
pthread_setaffinity_np failed … mask: {0,}from onnxruntime inmcp-stderr.logis a container affinity warning emitted on every model load — not an error. - See incidents/2026-10-03-mnemosyne-vector-recall-fts-only.
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
memorytable are not in the newworking_memory/episodic_memorysystem - These are only accessible via the legacy
memorytool, not viamnemosyne_recall
Gateway notifications were captured as user memories (fixed 2026-09-30)
- Hermes's background-process notifications (long-running
terminaljobs 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_defaultnamed the removed providercustom:omniinstead ofcustom: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 — script:
mnemosyne-health-monitor.sh, mode: no-agent since the 2026-11-08 conversion (jobea79a2107e36), reports only on exception. ⚠ The no-agent conversion was verified end-to-end on 2026-11-08: the 18:00 slot (agent mode) ran 12:00:51 → 18:00:42 = 5 h 59 m 51 s, and the converted job's first slot ran 2026-11-09 00:00:48 → 00:02:02 = 73 s, exit 0, silent —output/ea79a2107e36/2026-11-09_00-02-00.mdis 159 bytes against 105,982 B for the last agent-mode file. Live read at 2026-11-09 00:0x: working 1030/1030 = 100.0 %, episodic 1192/1192 = 100.0 % (so the< 95 %alert is correctly quiet), 1043 embeddings generated in 24 h. The script compares withawk, notbc—bcis not installed on this host (mnemosyne-health-monitor.sh:47), which is why the old monitor's arithmetic silently defaulted instead of failing loudly. ⚠ 2026-10-30: the monitor was twice flagged and neither flag survived contact withfinished_at. Its 00:01:08 slot was auto-paused at 01:04:22 on an "execution unverified / gateway connection failed" admission (incidents/2026-10-30-mnemosyne-health-monitor-paused) — but the slot was still running and closedcompletedat 10:02:48 after 10 h 01 m 40 s, delivering normally and auto-closing incidentea79a2_d93c3acdc4f2; the job is enabled,last_status: ok, streak 0. Its 12:01 slot was then lost to the CT460 host outage (5 h 30 m dark, incidents/2026-10-30-ct460-host-outage-scheduler-gap) and fired in the 16:37:21 catch-up. Checkfinished_atbefore believing a long-running slot failed. - Mnemosyne Embedding Coverage every 6h — job
b63ed5817212, alerts to Telegram topic 102 only when working-tier coverage drops below 95% - Mnemosyne Watchdog every 15m — script:
mnemosyne-watchdog.py, mode: no-agent - ⚠ Blast-radius note (2026-10-16). Both monitors above (
ea79a2107e36Health every 12 h,b63ed5817212Embedding Coverage every 6 h) are pinned tocustom:omni-101— the same node the memory system's own reporting depends on. During the 2026-10-14 → 10-15omniroute-1outage both failed on every slot, so no coverage figures were refreshed for ~34 hours; the last explicit read remains the 2026-10-12 12:02 run (working 760/786 = 96.7 %, episodic 1050/1056 = 99.4 %), and the 2026-10-16 00:09:48 Health Monitor run is the first clean read since. The two script-only jobs (consolidate_mnemosyne.sh,mnemosyne-backup.sh) were unaffected — they make no model call. Monitoring that shares a blast radius with its subject is degraded monitoring; a coverage alert that cannot fire during a router outage is exactly the case this has to cover. → incidents/2026-10-14-omniroute-node-connection-refused-storm
History and Evidence
- 2026-10-03: vector recall found running FTS-only (fastembed missing from the managed runtimes); repaired the same day and the dependency guard extended — see above and incidents/2026-10-03-mnemosyne-vector-recall-fts-only.
- 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 inrun_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: Nonecaused 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
Re-verified 2026-10-10 (audit window; live probes 2026-10-11 00:14-00:20 AWST)
- Gateway load path repaired. The gateway's
activate_dependencies()selects one committed uv env (795020dbf24343cd9c52df24723dca83); it was missingmnemosyne/mnemosyne_hermesand the native dependencies. Repaired 2026-10-10 21:26-21:34 and confirmed live from 22:01:19 (registered (40 tools)->activated). Detail: incidents/2026-09-28-hermes-managed-runtime-deps. - "Capture silent since 10-09 15:20" was a false alarm. It resolved to no interactive sessions
in the window - the window was cron-only traffic. What the surrounding hours did capture was
dominated by gateway background-process notifications stored as
[USER] [Anthony Martin] [IMPORTANT: Background process ...]rows: recall-visible, low signal. A capture filter would help; no fix applied (carried open item). - Coverage script executable again:
~/.hermes/scripts/check_embedding_coverage.pynow carries mode0755, so the monitor's non-executable finding is resolved. - Open, unverified: 13 orphan rows in
memory_embeddings(oldest 2026-08-22) reported by a 2026-10-10 monitor run - neither confirmed nor cleaned by this audit.
Re-verified 2026-10-18 (audit window; live probes 2026-10-18 00:30-00:36 AWST)
- Both monitors rode the
omniroute-1503 window; both are green again.ea79a2107e36(health, every 12 h) failed 10-17 00:00 withRuntimeError: HTTP 503 ... resource pressureand delivered its alert;b63ed5817212(coverage, every 6 h) failed 10-16 12:03 the same way. Since 10-17 12:00 every slot of both has completed withdelivery_outcome: suppressed(nothing to report) — including 10-18 00:00. - No fresh coverage figures exist in the ledger. These jobs report to Telegram, not to the execution row, so the last explicit read remains 2026-10-12 12:02 — working 760/786 (96.7 %), episodic 1050/1056 (99.4 %), both above the 95 % reindex threshold. Nothing here indicates a reindex is due.
- The watchdog triple-checks the same thing.
96eb95ce12f2(every 15 min) exited 1 four times — 10-16 12:15 + 12:30, 10-17 00:15 + 00:30 — each row quoting the coverage monitor's own 503 error, i.e. one sentinel producing four failure rows. Read failures per job, not per row. It has been clean on every slot since (latest 10-18 00:30).
Re-verified 2026-10-24 (audit window 2026-10-23; live probes 2026-10-24 00:1x–00:3x AWST)
- Cold start is the new failure vector for consumers: 10–45 s. The Conduit voice plugin
(
conduit_push) gave one request — provider start included — a hard-coded 10 s budget (MEMORY_TIMEOUT_S). Mnemosyne's cold start for theconduit-voicesession regularly exceeds that, so three calls were abandoned by the memory layer (10-22 11:28:17, 10-22 13:16:37, 10-23 18:29:16:Memory provider 'mnemosyne' start for Conduit timed out; abandoning the call), and the caller got an agent with no recall. Fixed in the plugin's working tree on 10-23: default 60 s, overridable withCONDUIT_MEMORY_TIMEOUT_S, plus aTokenErrorguard that logs and proceeds without recall instead of aborting. Dashboard restarted 18:54:43; no abort line exists after it. → incidents/2026-10-22-conduit-memory-start-timeout, systems/conduit - Rule for other consumers: a 10 s memory budget is below the observed cold-start floor. Any new surface that reads Mnemosyne on a first request needs ≥60 s, or must degrade to "no recall" rather than fail. The underlying cold start was not optimised — only the budget was raised.
- Capture and coverage unchanged from the 10-18 read (working 760/786 = 96.7 %, episodic 1050/1056 = 99.4 %; nothing indicates a reindex is due). No monitor reds in the window.