Memory Maintenance

Intelligent memory management for OpenClaw agents. Reviews daily notes, suggests MEMORY.md updates, maintains directory health, and auto-cleans old files. Recommended for agents with growing memory footprints.

Key things to consider before installing: - Privacy: The review script builds a prompt containing your recent daily notes, MEMORY.md, and USER.md and sends it to the Gemini CLI (external model). If those files contain sensitive data (passwords, tokens, personal data), they will be included in requests to an external service. Only install if you're comfortable with that or you sanitize files first. - .env export: The scripts source and export all variables from workspace/.env. Ensure that file does not contain other secrets you don't want exported or sent to the model. Consider giving GEMINI_API_KEY a restricted key or setting it only for this skill's runtime. - Hardcoded paths & portability: Several scripts use /Users/maxhutchinson/.openclaw/workspace hardcoded. This will likely fail or behave unexpectedly on other machines. Inspect and fix these paths (replace with OPENCLAW_WORKSPACE or $HOME/.openclaw/workspace) before installing broadly. - Review and test first: Run the review script in a safe test workspace (with non-sensitive sample files) to confirm behavior. Check where files are moved (archive/.trash) and verify the retention behavior meets your expectations. - Code quality issues: There are bugs (argument parsing in apply.sh mis-indents the --all handling) and rough edges; treat this as alpha software and review scripts before granting production use. - If you proceed: backup your workspace (or at least agents/memory and MEMORY.md), remove unrelated secrets from workspace/.env, and run install in a controlled environment. If you need strict privacy, do not use an external LLM or run the LLM step locally with a model you trust.

Type: OpenClaw Skill Name: memory-maintenance Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'memory-maintenance' is classified as benign. Its core functionality involves reading agent memory files (daily notes, MEMORY.md, USER.md) and sending them to the Gemini LLM API for analysis, using the provided GEMINI_API_KEY. While this involves handling sensitive data and interacting with an external service, it is explicitly stated as the skill's purpose and is not exfiltrated to an unauthorized endpoint. The skill implements robust safety features, including human review for content suggestions, dry-run modes, explicit confirmation for risky file operations, and moving deleted files to a trash directory for recovery. All file system operations and cron job additions are aligned with the stated memory maintenance and cleanup goals, without evidence of malicious intent or obfuscation.