SimpleMem provides efficient lifelong memory for LLM agents through semantic compression and intent-aware retrieval.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install simplemem
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install simplemem using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is SimpleMem?
SimpleMem is a high-performance memory management layer designed to provide AI agents with long-term, cross-session capabilities. By integrating this tool into your Openclaw Skills workflow, you enable agents to store, synthesize, and retrieve information with a multi-index approach that combines semantic, lexical, and symbolic layers. This ensures that agents remain contextual and personalized over extended periods without exceeding context window limits.
The system is engineered for efficiency, achieving significant improvements over standard memory implementations like Claude-Mem. It utilizes semantic compression to reduce data bloat while maintaining high accuracy, making it an essential component for developers building advanced Openclaw Skills that require a persistent and reliable 'brain' for their autonomous agents.
SimpleMem Use Cases
- Persistent user personalization for assistants that need to remember preferences across different sessions.
- Cost-effective context management for long-running research or development projects.
- Building autonomous agents that require a historical record of past actions and decisions.
- Implementing intent-aware retrieval to ensure only the most relevant context is sent to the LLM.
How SimpleMem Works
- Data Storage: Interactions are captured and stored as compact memory units.
- Semantic Compression: The system compresses these interactions to minimize token usage while preserving meaning.
- On-the-fly Synthesis: Related memory units are merged automatically to maintain a coherent and non-redundant knowledge base.
- Intent-Aware Retrieval: The skill uses specialized planning to retrieve the most relevant memories in under 388ms based on the current query intent.
SimpleMem Setup
To integrate this memory layer into your Openclaw Skills environment, follow these steps:
# Install the SimpleMem Python dependency
pip install simplemem
# Clone the repository for full access to scripts
git clone https://github.com/aiming-lab/SimpleMem.git
cd SimpleMem
pip install -r requirements.txt
To enable full semantic embedding features, configure your API key:
# For PowerShell
$env:OPENAI_API_KEY = "your-openai-key"
# For Bash
export OPENAI_API_KEY="your-openai-key"
SimpleMem Data Schema & Taxonomy
The skill organizes its data within a local structure to ensure privacy and speed. Below is the metadata and file taxonomy:
| File/Folder | Function |
|---|---|
| simplemem.py | The primary Python wrapper for API integration. |
| simplemem.ps1 | PowerShell script for command-line memory operations (add, search, stats). |
| data/ | Local directory created on first use to store persistent memory files. |
| memory_units | JSON or embedding-based files containing compressed interaction history and user_id tags. |
SimpleMem Advanced Features
- Cross-session persistence that performs 64% better than standard memory benchmarks.
- Multi-layered indexing including Semantic, Lexical, and Symbolic layers for high-precision retrieval.
- Automatic JSON fallback mode for basic keyword searching when an API key is not available.
- High-performance retrieval optimized for real-time agent responses with sub-400ms latency.
SKILL.md
Loading
Related Openclaw Skills
PDF Reader Skill
A high-performance text extraction tool designed to bridge the gap between static PDF documents and AI-ready data structures.
Open Notebook Integration
A local AI research assistant integration that provides agents with a persistent, private second brain for saving and querying thematic knowledge.
MCP Client
A versatile implementation of the Model Context Protocol (MCP) enabling AI agents to interact with standardized tools, data sources, and prompt templates.
askia-io
A command-line interface for the askia.io platform that enables AI agents to register, ask questions, and provide answers within a hybrid human-AI ecosystem.
The Hive Swarm Governance
A decentralized coordination protocol for AI agents using cryptographic identities, trust graphs, and consensus-driven code evolution.
Moltlog
A secure CLI tool designed to register AI agents and publish Markdown-formatted progress logs to the moltlog.ai platform.
METADATA
Featured*
