About Origin Memorycore
Origin Memorycore is an MCP server in the Healthcare category: lLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold.
Install
From source
git clone https://github.com/moonandecho/origin-memorycoreThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
memorycore_get_memory_usage()Hot-tier usage + cold-tier stats + thresholds
Parameters not published.
memorycore_get_rule_weight(target)Rule weight distribution (read-only cache monitor): w_eff, unified `priority`/`in_grace`, rule_chars vs budget, selector-accurate next eviction candidates
Parameters not published.
memorycore_memory_audit(target)Hot-tier health check: entry types, age, keep/sink plan, cache-policy observability (`priority`, `in_grace`, `next_evict`), timestamp anomalies
Parameters not published.
memorycore_recall(query, top_k, handle)Actively recall cold-tier memories (read-only, complements per-turn prefetch). `handle` supports direct pointer/page-fault lookup
Parameters not published.
memorycore_run_cold_storage_maintenance()Cold-tier governance pass
Parameters not published.
memorycore_set_entry_type(target, match_text, type_override, protect_override)Manual sidecar-only annotation (`state`/`rule`, protect override); takes effect on the next overflow
Parameters not published.
memorycore_trigger_overflow(target)Run six-step overflow, target ≤40%
Parameters not published.
Ask AI
✦
Ask AI about Origin Memorycore
Powered by Claude · Grounded in docs
I know everything about Origin Memorycore. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.