MCP.so
登录

OpenClaw Memory Health

@ladyiceberg

关于 OpenClaw Memory Health

External QA layer for OpenClaw memory — diagnose, guard, and remediate your agent's memory.

基本信息

分类

记忆与知识

传输方式

stdio

发布者

ladyiceberg

提交者

ladyiceberg z

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "openclaw-memhealth": {
      "command": "uvx",
      "args": [
        "openclaw-memory-quality"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is OpenClaw Memory Health?

OpenClaw Memory Health is an external QA layer that diagnoses, guards, and remediates an agent’s memory in the OpenClaw memory system. It addresses the silent degradation caused by OpenClaw’s additive-only memory model, which leads to stale long‑term memories, false‑positive short‑term entries, and identity drift in SOUL.md.

How to use OpenClaw Memory Health?

Use the six provided functions to intercept the memory pipeline at key stages: memory_health_check_oc(), memory_longterm_audit_oc(), memory_promotion_audit_oc(), memory_soul_check_oc(), memory_config_doctor_oc(), and memory_dashboard_oc(). An LLM API key is optional, and all read‑only tools are safe.

Key features of OpenClaw Memory Health?

  • Quick memory health scan with zombie count, false‑positive rate, and retrieval score
  • Deep audit of MEMORY.md for source validity and duplicate detection
  • Pre‑promotion quality gate with five checks before entries enter MEMORY.md
  • SOUL.md boundary violation and identity drift audit
  • Inferred minScore and embedding issue diagnosis from behavior data
  • Bilingual visual health dashboard (Chinese/English)

Use cases of OpenClaw Memory Health

  • Detect and remove zombie memory

评论

记忆与知识 分类下的更多 MCP 服务器