six-layer-memory

Set up or repair a proactive six-layer memory system for an OpenClaw/Codex workspace. Use when a user wants durable HOT/WARM/COLD/CURATED/CLOUD/AUTO memory, periodic maintenance, per-workspace memory files, optional SuperMemory sync, and automatic fact extraction without losing context across restarts.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "six-layer-memory" with this command: npx skills add ashu2025-rgb/six-layer-memory

Six-Layer Memory

Use this skill when the user wants a workspace to keep memory proactively instead of relying on chat context alone.

What this skill sets up

  • HOT: memory/SESSION-STATE.md
  • WARM: local vector/index refresh when source material changes
  • COLD: memory/decisions/
  • CURATED: MEMORY.md plus daily logs
  • CLOUD: optional SuperMemory sync
  • AUTO: optional Mem0-backed fact extraction

Workflow

  1. Pick the target workspace.
  2. Run scripts/install_workspace.sh <workspace>.
  3. Configure AUTO: Use LM Studio if the machine already has a local chat model and embedding model. Use Ollama only if both the chat model and embedding model are actually available.
  4. Configure CLOUD if the user wants cross-device recall: Put a SuperMemory key in memory/auto-extract/.supermemory_key.
  5. Add periodic execution:
59 23 * * * /usr/bin/python3 <workspace>/memory/auto_memory_6layer.py --workspace <workspace> --daily --source wal-daily
0 6 * * * /usr/bin/python3 <workspace>/memory/auto_memory_6layer.py --workspace <workspace> --daily --source memory-daily-sync
*/30 * * * * /usr/bin/python3 <workspace>/memory/auto_memory_6layer.py --workspace <workspace> --source memory-sync
  1. Validate with memory/check_memory_layers.sh.

Bundled scripts

  • scripts/install_workspace.sh
  • scripts/auto_memory_6layer.py
  • scripts/supermemory_sync.py
  • scripts/mem0_sync.py
  • scripts/memory_writer.py
  • scripts/check_memory_layers.sh

Notes

  • This skill is designed per workspace. Repeat installation for each agent workspace.
  • Do not overwrite HOT state with synthetic “all good” status text.
  • Prefer one canonical HOT file path: memory/SESSION-STATE.md.
  • Keep MEMORY.md for durable facts only. Put operational notes elsewhere.

References

  • Beginner setup guide (Chinese + English): references/beginner-guide-zh-en.md
  • Release copy draft (Chinese + English): references/release-notes-zh-en.md

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Open Registry RecordOpen in ClawHub

Related Skills

Related by shared tags or category signals.

Coding

🧠 Memory Never Forget 🧠

Memory system v4.13: Dual-layer structure (todos for execution + knowledge for strategy) with Dream/Refinement memory mechanisms.

Registry SourceRecently Updated
3.3K3Profile unavailable
Coding

Context Hawk

Pure Python memory manager for preserving and retrieving multi-layered AI memories across sessions, topics, and time without external dependencies.

Registry SourceRecently Updated
2040Profile unavailable
Coding

Cheat Code

Makes your agent's talents limitless. Tell your agent what you want. Watch it deliver.

Registry Source
1.5K2Profile unavailable
General

Memory Auto Archive

Automatically archives daily chat logs with keyword highlights and optional AI summaries into organized memory files without manual setup.

Registry SourceRecently Updated
2820Profile unavailable