OpenClaw Memory Health
About
External QA layer for OpenClaw memory — diagnose, guard, and remediate your agent's memory.
Details
- Author
- ladyiceberg
- Downloads
- 303
- Categories
- Knowledge Base, AI
Jump to
- 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)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
OpenClaw Memory HealthCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"openclaw memory health": {
"openclaw-memhealth": {
"command": "uvx",
"args": [
"openclaw-memory-quality"
]
}
}
}
}McpServers
{
"openclaw-memhealth": {
"command": "uvx",
"args": [
"openclaw-memory-quality"
]
}
}External QA layer for OpenClaw memory — diagnose, guard, and remediate your agent's memory.
OpenClaw only adds to memory, never removes. Over time this causes silent degradation: stale long-term memories pointing to
deleted files, false-positive short-term entries getting promoted, and SOUL.md drifting with task instructions that don't belong
in an identity file.
openclaw-memhealth intercepts the memory pipeline at every stage:
• memory_health_check_oc() — quick scan: zombie count, false-positive rate, retrieval health score
• memory_longterm_audit_oc() — deep audit of MEMORY.md: source validity, duplicate detection
• memory_promotion_audit_oc() — pre-promotion quality gate: 5 checks before entries enter MEMORY.md
• memory_soul_check_oc() — audit SOUL.md for boundary violations and identity drift
• memory_config_doctor_oc() — infer minScore/embedding issues from behavior data
• memory_dashboard_oc() — visual health dashboard with bilingual support (zh/en)
LLM API key optional. All read-only tools are zero-risk.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
