Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
**Expanded workflow and clarified security for agent persistent memory** - Updated documentation with explicit instructions for session management (start, remember, recall, forget, end). - Added detailed API parameter explanations and usage scenarios for memory actions. - Clarified security boundaries: installation is always manual, no automatic file writes or remote actions. - Expanded security/defence section with step-by-step defence pipeline and Iron Dome behavioural security features. - Added knowledge graph usage and memory intelligence tooling (contradiction detection, consolidation, stats). - Included Universal Memory Bridge instructions for securing external backends.
What This Skill Does
Persistent memory system for AI agents backed by SQLite with semantic search, knowledge graphs, decay-based forgetting, and contradiction detection. Every memory write passes through a 6-layer defense pipeline that blocks prompt injection, credential leaks, and poisoning attacks. Iron Dome adds behavioral protection with configurable action gates, security profiles, and a full forensic audit trail.
Combines persistent semantic memory and security defense in one package, eliminating the need to wire separate memory and threat-detection systems together.
When to use it
- Recalling architecture decisions from a previous coding session
- Detecting prompt injection patterns in agent instruction files
- Blocking accidental API key writes to agent memory
- Persisting user preferences across multiple project workspaces
- Auditing all memory reads and writes for a security review
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Remember that the payment API requires OAuth2 bearer tokens, not API keys
- 1Receive memory write request with content and project scope
- 2Run content through the 6-layer defence pipeline to check for injection patterns and credential leaks
- 3Store approved memory in SQLite with importance level and category set to 'architecture'
- 4Extract knowledge graph entities and relationships from the memory content
- 5Check for contradictions with existing memories and confirm storage
Memory stored under category 'architecture' with entities ['payment API', 'OAuth2'] and a relationship triple added to the knowledge graph