Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
FINAL: Metadata integrity fix & proper display name 🎯 REGISTRY METADATA RESOLVED: ✅ Fixed 'instruction-only' vs installable inconsistency ✅ Proper display name: 'Rune - Self-Improving AI Memory' ✅ Clear installation specifications in registry metadata ✅ Accurate reflection of install.sh and workflow components 🔧 WHAT THIS FIXES: • Registry now correctly shows this as installable skill • Display name shows 'Rune' instead of generic 'Skill' • Installation metadata properly synchronized • Clear documentation of system-level integration requirements ⚠️ IMPORTANT: This is an INSTALLABLE skill with system integration • Modifies ~/.openclaw/workspace/HEARTBEAT.md • Creates workflow automation scripts • Includes session hooks for automatic memory usage • Intrusive by design to prevent memory system non-usage 📋 FINAL PRODUCTION-READY RELEASE Complete memory system with workflow integration, security fixes, and accurate metadata. Ready for users who want systematic memory usage.
What This Skill Does
Rune gives an OpenClaw agent persistent memory stored in a local SQLite database. It dynamically selects relevant facts per conversation rather than loading everything at once, and applies forgetting curves so stale information fades over time.
Injects only contextually relevant facts per conversation instead of loading a full static context file, reducing token usage while keeping responses more accurate.
When to use it
- Remembering why a technical decision was made weeks later
- Getting prioritized task suggestions when unsure what to work on next
- Tracking which tools or approaches caused problems in past sessions
- Detecting when a project has stalled and needs attention
- Adapting to whether a session is exploratory brainstorming or focused debugging
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: What should I work on next?
- 1Runs `rune inject` to load relevant facts into session context
- 2Runs `rune next-task` to retrieve priority-scored task recommendations
- 3Checks `rune stuck-projects` to surface any blocked work
- 4Returns the top task with its priority score and relevant memory context
Top recommended task with priority score, relevant project facts, and any identified blockers
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.