Memory Optimizer

提供基于SHA-256的重复记忆去重、后台实时更新和90天记忆自动归档的OpenClaw高效记忆管理方案。

This package appears to do what it says: local SHA-256 deduplication + a watchdog-based listener. Before installing: 1) Inspect the scripts (you already have them) and confirm there are no network calls — none are present. 2) Note the missing memory-archive.sh referenced in docs/README.md and SKILL.md; if you need the archive step, either obtain that script from the author repository or implement your own archive process. 3) install.sh will copy files into ~/.openclaw/workspace and run 'pip3 install watchdog' — if you prefer, run the pip command in a virtualenv. 4) Back up any existing ~/.openclaw/workspace/memory/.index.json before running to avoid accidental overwrite. 5) If you have concerns about provenance, prefer installing from a trusted repository URL (skill.json lists a GitHub repo/homepage) or ask the author for a signed release.

Type: OpenClaw Skill Name: memory-optimizer Version: 1.0.0 The memory-optimizer skill bundle is a legitimate utility designed to manage and optimize OpenClaw agent memory files through SHA-256 deduplication and real-time monitoring. The Python scripts (memory-dedup.py and memory-watcher.py) use standard libraries like hashlib and watchdog to index and track changes in Markdown files within the user's workspace. No evidence of data exfiltration, malicious persistence, or prompt injection was found; the code is well-documented and its behavior aligns perfectly with its stated purpose.