An automated memory synchronization system that bridges local Markdown files and CortexGraph using intelligent forgetting curves.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memory-sync-cn
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 memory-sync-cn 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 Memory Sync System (CortexGraph)?
The Memory Sync System is a sophisticated architectural layer designed to manage AI agent memory using the Ebbinghaus forgetting curve algorithm. It facilitates seamless synchronization between long-term memory stored in MEMORY.md, daily activity logs, and the CortexGraph intelligent layer. By leveraging Openclaw Skills, developers can ensure their agents retain high-value information while naturally pruning low-relevance data, mimicking human cognitive processes for more efficient context management.
This system acts as a bridge between static documentation and active AI reasoning. It allows agents to not only remember facts but to prioritize them based on frequency of use and temporal relevance. Integrating this within the ecosystem of Openclaw Skills empowers developers to build agents with a truly persistent and evolving personality.
Memory Sync System (CortexGraph) Use Cases
- Automated synchronization of long-term memory (MEMORY.md) with active AI knowledge graphs.
- Intelligent pruning of temporary data using decay models to prevent context window bloat.
- Promotion of high-value daily logs into permanent knowledge repositories like Obsidian vaults.
- Enhancing AI responsiveness through semantic search and automatic recall of relevant past interactions using Openclaw Skills scripts.
How Memory Sync System (CortexGraph) Works
- The system imports existing MEMORY.md content into CortexGraph to establish a baseline intelligent knowledge layer.
- Daily log files formatted as YYYY-MM-DD.md are synchronized to capture ongoing interactions and temporal context.
- The Ebbinghaus forgetting curve algorithm calculates memory scores based on usage frequency, decay constants, and importance strength.
- High-scoring candidate memories are promoted to long-term storage while garbage collection is performed on low-score entries to maintain system hygiene.
- Intelligent analysis tools decide in real-time whether a new message should be saved or if previous memories should be recalled during an active session.
Memory Sync System (CortexGraph) Setup
To get started with this component of Openclaw Skills, install the necessary dependencies:
# Install Python and Node.js components
pip install cortexgraph
npm install -g mcporter
Configure your environment variables in ~/.config/cortexgraph/.env to point to your storage and vault paths:
# Storage path for memory entries
CORTEXGRAPH_STORAGE_PATH=~/.config/cortexgraph/jsonl
# Decay and promotion thresholds
CORTEXGRAPH_PROMOTE_THRESHOLD=0.65
LTM_VAULT_PATH=~/Documents/Obsidian/Vault
Memory Sync System (CortexGraph) Data Schema & Taxonomy
The system organizes data across three primary layers to ensure structural clarity:
| Component | Format | Purpose |
|---|---|---|
| MEMORY.md | Markdown | Long-term permanent storage and manual human reference. |
| CortexGraph | JSONL/Vector | Intelligent layer with decay metadata, entities, and embeddings. |
| Daily Logs | Markdown | Temporal snapshots of daily activities and short-term context. |
Memory scoring follows the formula: score = (use_count)^β * e^(-λ * Δt) * strength, where β represents use weight and λ is the decay constant.
Memory Sync System (CortexGraph) Advanced Features
- Power-law decay models for fine-tuned control over how quickly the AI forgets specific information.
- Multi-stage memory promotion logic that moves data from daily logs to permanent Obsidian vaults based on importance.
- Automated memory consolidation to merge similar entries, reducing redundancy and improving search accuracy.
- Full integration with Openclaw Skills via mcporter, allowing for command-line memory management and health checks.
- Garbage collection (GC) and backfill embedding support to maintain a high-performance vector database.
SKILL.md
Loading
Related Openclaw Skills
MBTI Agent - Digital Sprite Personality Assessment
A specialized psychometric framework for evaluating the personality profiles of non-interactive AI agents using a static 70-question assessment.
Market Analysis Service
A data-driven analytical suite providing industry trends, competitor deep dives, and user behavior insights.
Lead Research Assistant
An AI-powered assistant designed to identify high-quality sales leads and generate actionable outreach strategies based on your specific product or service.
Jike Hot Topics Monitor
A specialized monitoring tool for tracking real-time trending topics and community discussions on the Jike social platform.
Memory Sync Enhanced
A dual-layer AI memory architecture that mimics human biological forgetting and associative learning patterns to optimize context relevance.
ML Evolution Agent
An autonomous machine learning agent that iteratively evolves models and leverages multi-layer memory to dominate Kaggle competitions and tabular data tasks.
Featured*
