An edge-optimized RAG memory system that provides AI agents with persistent, semantic long-term memory using minimal system resources.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-memory-enhancer
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 openclaw-memory-enhancer 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 OpenClaw Memory Enhancer?
The OpenClaw Memory Enhancer is a sophisticated memory layer designed for the Openclaw Skills ecosystem, enabling AI agents to retain and recall information across multiple sessions. It implements a Retrieval-Augmented Generation (RAG) system that automatically processes files from a memory directory, providing agents with the context needed to maintain continuity in long-term projects and personalized user interactions.
What sets this skill apart is its high level of optimization for edge computing. It offers a specialized Edge version that runs with zero external dependencies and consumes less than 10MB of RAM, making it ideal for devices like the NVIDIA Jetson or Raspberry Pi. By utilizing local storage, it ensures that all memory data remains private and secure on the user's hardware without needing cloud-based vector databases.
OpenClaw Memory Enhancer Use Cases
- Enabling AI agents to remember user preferences and past decisions across different chat sessions.
- Building a local knowledge base automatically from historical conversation logs.
- Providing deep context for long-term technical projects where the agent needs to track progress.
- Generating automated FAQs or solution guides based on previous problem-solving interactions.
- Deploying intelligent agents on resource-constrained hardware where traditional RAG stacks are too heavy.
How OpenClaw Memory Enhancer Works
- Memory Encoding: The system extracts keywords from text and converts them into normalized hash vectors.
- Automated Loading: It scans the specified memory directory to ingest existing Markdown or JSON files into the local vector store.
- Semantic Search: When a query is received, the system performs a fast keyword pre-filter followed by a cosine similarity calculation.
- Ranking and Retrieval: The most relevant memory chunks are ranked and retrieved based on a configurable similarity threshold.
- Prompt Enhancement: Relevant context is injected into the LLM prompt, allowing the agent to provide informed responses based on historical data.
OpenClaw Memory Enhancer Setup
To install via ClawHub, use the following command:
clawhub install openclaw-memory-enhancer
For manual installation via Git:
git clone https://github.com/henryfcb/openclaw-memory-enhancer.git ~/.openclaw/skills/openclaw-memory-enhancer
To initialize the edge-optimized version and load memories:
cd ~/.openclaw/skills/openclaw-memory-enhancer
python3 memory_enhancer_edge.py --load
OpenClaw Memory Enhancer Data Schema & Taxonomy
The skill organizes data within the ~/.openclaw/workspace/knowledge-base/ directory using a structured taxonomy to improve Openclaw Skills retrieval accuracy:
| Memory Type | Description | File Context |
|---|---|---|
daily_log |
Chronological activity | memory/YYYY-MM-DD.md |
core_memory |
Fundamental agent rules | System instructions |
qa |
Question and Answer pairs | FAQ generation |
preference |
User-specific settings | Personalization data |
solution |
Technical walkthroughs | Implementation guides |
Storage is maintained in lightweight JSON formats for the Edge version or NumPy-backed arrays for the Standard version.
OpenClaw Memory Enhancer Advanced Features
- Dual-Engine Support: Choose between a zero-dependency Edge version (<10MB RAM) or a Standard version using sentence-transformers for maximum accuracy.
- Memory Graph: Automatically builds connections between related memories to enable complex context traversal.
- Python API Integration: Developers can import the MemoryEnhancer classes directly into custom agent scripts for deep integration.
- Automatic Pruning: Configurable memory limits that automatically manage storage by removing the oldest, least relevant records.
- Local-First Privacy: Operates entirely without network requests, ensuring no data ever leaves the local environment.
SKILL.md
Loading
Related Openclaw Skills
Task Orchestrator
An autonomous orchestration skill for managing multi-agent development tasks using tmux, Codex, and intelligent dependency analysis.
BMAD Orchestrator
A comprehensive orchestration skill that manages the 4-phase BMAD Method across OpenClaw and Claude Code for agile, AI-driven development.
Henteplan - Norwegian Waste Collection
A specialized tool for Norwegian households to query waste collection schedules and set up automated bin reminders.
Kalshi Prediction Markets
A read-only Kalshi integration for browsing prediction markets and analyzing trade opportunities through Openclaw Skills.
Feishu Deep Research
An automated research agent that conducts deep data gathering and generates structured reports directly in Feishu cloud space.
Feishu Folder Summary
A powerful tool for recursively scanning Feishu folders and wiki spaces to generate comprehensive, structured Markdown summary reports.
Featured*
