Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Clarify self-hosted architecture: no maasv cloud, user owns all data, only external calls are to user's own LLM provider
What This Skill Does
A self-hosted memory backend for OpenClaw agents that uses three retrieval signals: semantic similarity, keyword matching, and a knowledge graph. Includes entity extraction, temporal versioning, and experiential learning. All data lives in a SQLite file on your local machine; nothing is sent to any maasv service.
Combines semantic, keyword, and graph-based retrieval in a single self-hosted system, so agents get richer memory recall without sending conversation data to a third-party service.
When to use it
- Recalling project decisions made in past agent sessions
- Tracking entities and relationships across long-running workflows
- Running agent memory with no cloud data storage
- Searching past reasoning and outcomes when facing similar problems
- Persisting conversation context between separate agent invocations
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: 'Remember that we decided to use PostgreSQL for this project because of the JSON query requirements'
- 1Calls memory_store with the decision summary
- 2maasv server runs entity extraction, identifying 'PostgreSQL' and 'JSON query requirements' as entities
- 3Entities and relationships are written to the local SQLite database
- 4In a later session, autoRecall queries the memory store
- 5Injects the relevant context into the agent before it responds
Memory stored locally and surfaced automatically in future sessions when the topic is relevant
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.