A sophisticated three-tier memory architecture that integrates vector databases, structured git-based notes, and local file search for total context persistence.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install triple-memory-skill
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 triple-memory-skill 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 Triple Memory System?
The Triple Memory System is a comprehensive context management framework designed to solve the problem of information loss in AI agent sessions. By combining three complementary storage backends, it ensures that your Openclaw Skills retain critical project decisions, user preferences, and historical data across different environments and branches.
This system leverages LanceDB for semantic auto-recall, Git-Notes for branch-specific structured data, and local markdown files for human-readable workspace documentation. It provides a robust safety net that automatically flushes context to persistent storage before token limits are reached, making it ideal for long-term development projects.
Triple Memory System Use Cases
- Maintaining persistent developer preferences and architectural decisions across multiple coding sessions.
- Tracking branch-specific context in Git-based workflows to ensure memory stays relevant to the current task.
- Automatically summarizing and archiving chat history when nearing context window limits.
- Performing semantic searches across past conversations to retrieve specific facts or code snippets.
- Creating a curated, human-readable MEMORY.md file for project-level documentation.
How Triple Memory System Works
- Auto-Recall: When a user message is received, the system queries LanceDB to inject relevant conversation memories directly into the prompt.
- Response Generation: The AI agent processes the request utilizing the combined context from all three memory layers.
- Auto-Capture: LanceDB automatically identifies and stores new preferences, facts, or decisions from the agent's response.
- Structured Logging: The Git-Notes component extracts entities and records decisions with specific importance levels and tags.
- Workspace Update: Local files like MEMORY.md and daily logs are updated to maintain a persistent, version-controlled record of the workspace state.
Triple Memory System Setup
To integrate this system into your Openclaw Skills, follow these configuration steps:
- Install Git-Notes Memory:
clawdhub install git-notes-memory
Configure LanceDB Plugin: Add the memory-lancedb plugin to your configuration with your API key and auto-recall settings enabled.
Enable Auto Memory Flush: Configure the
compactionsettings in your agent defaults to trigger amemoryFlushwhen the context reaches 80% (approx 8000 tokens).Deploy Search Scripts: Copy the
file-search.shutility to your project'sscripts/directory to enable local workspace indexing.
Triple Memory System Data Schema & Taxonomy
The Triple Memory System organizes information into a hierarchical structure within your workspace:
| Location | Purpose | Format |
|---|---|---|
MEMORY.md |
Long-term curated project context | Markdown |
memory/active-context.md |
Real-time session state tracking | Markdown |
memory/YYYY-MM-DD.md |
Daily session logs and summaries | Markdown |
skills/git-notes-memory/ |
Structured, branch-aware entity storage | Git-Notes |
scripts/file-search.sh |
Local file indexing and retrieval | Shell Script |
Triple Memory System Advanced Features
- Auto Memory Flush: A safeguard mode that automatically preserves session context to files and vector storage before token compaction occurs.
- Branch-Aware Memory: Isolation of memories per Git branch, ensuring that experimental code context doesn't pollute the main branch history.
- Importance Level Flags: Tag memories as Critical, High, Normal, or Low to prioritize which information is recalled during high-density sessions.
- Entity Extraction: Automatic identification of names, concepts, and technical topics for structured retrieval.
- Silent Operation: Background memory management that operates without intrusive status updates, keeping the conversation focused on the task.
SKILL.md
Loading
Related Openclaw Skills
Browser Ladder
A cost-optimized web automation framework that escalates from simple fetches to premium cloud browsers only when necessary.
SupaSkills
A comprehensive library of over 1,000 quality-scored expert skills designed to give AI agents deep domain-specific expertise.
Vercel React Composition Patterns
A professional framework for building flexible React components using compound patterns and state decoupling to eliminate boolean prop proliferation.
QR Coin Auction
A blockchain automation skill for participating in decentralized QR code URL auctions on the Base network.
Triple Memory System
A comprehensive three-tier memory architecture combining vector search, structured local notes, and workspace file indexing for AI agents.
Social Media Ops
A comprehensive multi-agent framework that scaffolds a specialized seven-agent team to manage multi-brand social media operations with automated workflows and approval gates.
Featured*
