AI自我优化的记忆skills
Workspace memory lifecycle system. Dual-layer Bayesian decay + four-state quality gate + case lifecycle + compaction.
memory_status firstMG_WORKSPACEmg_schema/meta_defaults.pyworkspace defaults from MG_WORKSPACE env var; only non-default params listed.
Query
memory_status() — System overview (memory count / gate state / case summary / references integrity)memory_query(type="active", min_score=0.3) — Search memories (keyword/memory_type filter)Write
memory_ingest(content="...", importance="auto", tags=[]) — Create new memorymemory_decay(lambda=0.01, dry_run=false) — Run five-track Bayesian decayAudit
quality_check(layer="all") — Quality gate (retire_rate / similar_case_signal / stale_cases)case_query(filter="frozen") — Query cases (active/frozen/retired/stale/ignored)case_review(case_id, action="retire", origin_type="agent_initiated") — Case operations (active/frozen/retired/unfreeze/ignore)Batch
run_batch(skip_compact=true, dry_run=false, timeout=300) — Full maintenance (includes sync + signal merge)memory_sync(dry_run=true) — Sync file changes → meta.json (auto-run in run_batch)memory_compact(dry_run=true, aggressive=false) — Compact MEMORY.mdmemory_status → confirm references.complete: truerun_batch(skip_compact=true) runs automatically. Includes:
D1: Memory bloat → memory_compact(dry_run=true) → apply if needed → see compaction.md
D2: Quality anomaly → quality_check(layer="all") → see error_recovery.md
D3: Case invalidation → case_query(filter="stale") → case_review(action="retire"|"active"|"unfreeze") → see case-management.md
Dual-layer access signals feed the decay engine:
access_log.jsonl — agent appends after memory_getAgent must append to access_log.jsonl after each memory_get call. See signal-loop.md for integration code.
Load on demand per scenario:
When MCP unavailable, CLI path relative to skill dir:
python3 scripts/memory_guardian.py <command> [--workspace <path>]
Commands: status, ingest, bootstrap, snapshot, run, violations, migrate