Memory/skill entropy: project-specific tactical data silently degrades agent quality over time

Description and use

Adding a lightweight memory audit to Hermes Agent flags project‑specific data, preventing it from degrading agent decisions.

Problem

After weeks of daily use, the agent’s decisions degrade because project‑specific tactics accumulate in memory and are applied to unrelated projects, creating "experience debt."

Outcome

Adding a simple audit function reduces memory noise, preventing project‑specific tactics from leaking into unrelated contexts and improving agent performance.

Workflow

• 1. Define STALE_PATTERNS regex list for project‑specific data.
• 2. Implement memory_audit(entry) to return warnings if patterns match.
• 3. Hook memory_audit into the memory write path; if warnings are returned, add a warning to the tool response.
• 4. Optionally flag entries older than N writes for review during read.
• 5. Run the audit regularly to keep memory clean.

Evidence

Add a lightweight memory_audit function that runs on write and flags entries containing project-specific patterns

Source

This issue is the automation of that exact cleanup.

Source