domains / families / agent-tooling / memory-feedback

memory-feedback

separate

Agent memory and learning system. Logs actions/failures, detects patterns, proposes skill improvements via GitHub PRs. Human approval required.

When to use

• logging episodes and failures
• detecting patterns in logs
• proposing skill improvements
• creating GitHub pull requests
• managing rate limits
• viewing memory data

When not to use

• automatically merging skill changes
• acting on weak evidence below confidence threshold

Skill page

Source