OpenClaw Memory Health

Name: OpenClaw Memory Health
Author: ladyiceberg

@ladyiceberg

リポジトリ

OpenClaw Memory Health について

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

#openclaw #memory #mcp #memory-health #agent #llm #ai-agent #soul

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

公開者

ladyiceberg

投稿者

ladyiceberg z

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

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

「メモリとナレッジ」の他のコンテンツ

Docs MCP Server

arabold

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

1.5K

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763

minutes

silverstein

Every meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.

1.3K

Basic Memory

basicmachines-co

AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN

3.4K

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425