Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- No changes detected in this version. The skill remains at version 1.0.0 with no file updates.
What This Skill Does
SimpleMem gives LLM agents persistent memory across sessions by compressing interactions into compact units and retrieving them based on intent. It uses a multi-index approach combining semantic, lexical, and symbolic layers. Without an OpenAI key, it falls back to JSON-based keyword search.
Unlike naive context stuffing, SimpleMem compresses and indexes memories so retrieval stays fast and relevant even as history grows.
When to use it
- Remembering user preferences across chat sessions
- Storing project context for long-running agent tasks
- Reducing repeated context in multi-turn conversations
- Retrieving relevant past interactions during planning
- Compressing conversation history to stay within token limits
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Remember that I prefer dark mode and always use TypeScript
- 1Calls simplemem add with the preference string and a user ID
- 2SimpleMem compresses and stores the memory unit in persistent storage
- 3In a later session, agent calls simplemem retrieve with query about user preferences
- 4SimpleMem runs intent-aware search across semantic and lexical indexes
- 5Returns ranked memory results with the stored preference
Agent recalls dark mode and TypeScript preference without re-prompting the user
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.