How do I install the Openclaw Mem Sync skill?

Run npx skillmds@latest add phenomenoner/openclaw-mem-sync in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Openclaw Mem Sync skill do?

Govern embedding refresh, episodic evidence synchronization, metadata writeback, and engine dataset snapshots. Use before or after bounded sync, reindex, migration, or writeback operations. It is listed under AI & ML on SkillMD.

Is Openclaw Mem Sync safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openclaw Mem Sync?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openclaw Mem Sync free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openclaw Mem Sync?

phenomenoner (@phenomenoner) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openclaw Mem Sync by phenomenoner — Agent Skill

Name: Openclaw Mem Sync
Rating: 4.2 (5 reviews)
Author: phenomenoner

File contents

Sync Governance

Boundaries

Keep episodic evidence distinct from durable facts.
Refresh only the requested scope, field, model, and bounded limit.
Snapshot engine datasets before mass writeback, reindex, migration, or checkout.
Require receipts and explicit confirmation for destructive or active-dataset actions.
Treat model/dimension and orphan-vector warnings as integrity issues to investigate.

Operate

openclaw-mem episodes embed --scope <scope> --limit 500 --json
openclaw-mem episodes search <query> --scope <scope> --mode hybrid --trace --json
openclaw-mem embed --field both --limit 500 --json
openclaw-mem db info --json
openclaw-mem engine snapshot create --tag <tag> --reason <reason> --json
openclaw-mem writeback-lancedb --lancedb <path> --table <table> --dry-run --json

Use OPENCLAW_MEM_EMBED_PROVIDER=local only with the embed extra installed. Local and OpenAI model rows may coexist; query the same stored model deliberately.

Verify

openclaw-mem db info --json
openclaw-mem doctor --json
python -m pytest tests/test_embedding_providers.py tests/test_embedding_integrity.py -q

Frequently asked questions

Openclaw Mem Sync