domains / families / agent-tooling / memory-hygiene

memory-hygiene

combined

Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is high from irrelevant auto-recalls, or setting up memory maintenance automation. Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims against the live environment, stamps last_verified + confidence, and proposes archiving drifted entries

When to use

• Audit vector memory
• Clean bloated memory
• Optimize LanceDB
• Disable auto-capture
• Reseed key facts
• Set up maintenance automation
• Re-verify environment-dependent claims
• Propose archiving drifted entries

When not to use

• Storing heartbeat status
• Storing transient info
• Storing raw message logs
• Storing OAuth URLs or tokens

Skill page

Conflict

The two copies describe different memory-hygiene procedures for different systems. The first is a trust sweep of persistent notes that re-verifies environment-dependent claims, stamps last_verified/confidence, and proposes archiving drifted entries. The second is a vector-memory (LanceDB) maintenance workflow that audits, wipes, reseeds, disables auto-capture, and schedules monthly maintenance. They overlap only in the high-level idea of keeping memory clean, but each contains material steps and constraints the other lacks, so crowning one would hide a real alternative.