A persistent memory management skill that allows AI agents to store, recall, and search knowledge using the Quack Network FlightBox.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install quack-memory
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 quack-memory 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 Quack Memory?
Quack Memory is a critical component of the Openclaw Skills ecosystem designed to provide AI agents with a long-term memory layer. By leveraging the FlightBox API on the Quack Network, this skill enables agents to persist facts, lessons, and decisions across different sessions, preventing the loss of important context.
This skill transforms ephemeral agent interactions into a searchable, chronological knowledge base. Whether you are building a complex automation or a simple assistant, integrating Quack Memory ensures that your Openclaw Skills can learn from past experiences and maintain consistency over time.
Quack Memory Use Cases
- Storing lessons learned during code execution to avoid repeating errors.
- Persisting user preferences and specific context across multiple agent sessions.
- Creating a chronological timeline of agent decisions for auditing purposes.
- Searching for specific facts or data points previously encountered by the agent.
- Synchronizing knowledge between different agents within the Openclaw Skills framework.
How Quack Memory Works
- The agent identifies information that needs to be persisted, such as a lesson or fact.
- The skill authenticates with the Quack Network using a secure API key stored in the local credentials directory.
- Data is sent to the FlightBox API where it is indexed for semantic search and chronological retrieval.
- When context is needed, the agent performs a query to recall relevant memories based on similarity or specific tags.
- The agent integrates the retrieved memory into its current reasoning process to provide more accurate responses.
Quack Memory Setup
First, ensure you have registered your identity using the quack-identity skill. Then, extract your API key to ensure the environment is ready for Openclaw Skills integration.
# Load the Quack API key from your local credentials
QUACK_KEY=$(node -p "JSON.parse(require('fs').readFileSync(require('os').homedir()+'/.openclaw/credentials/quack.json','utf8')).apiKey")
To store a memory using the provided scripts:
node {baseDir}/scripts/remember.mjs --type "lesson" --content "Always verify before reporting" --tags "safety,ops" --importance 0.9
To recall memories based on a query:
node {baseDir}/scripts/recall.mjs --query "user preferences" --limit 5
Quack Memory Data Schema & Taxonomy
Quack Memory organizes data through the FlightBox API with a focus on semantic utility. The following table describes the primary data attributes used within these Openclaw Skills:
| Field | Description | Type |
|---|---|---|
| id | Unique identifier for the memory (e.g., mem_7f3a2b) | String |
| type | Classification: decision, fact, lesson, todo, or context | Enum |
| content | The actual text or knowledge to be stored | String |
| tags | Comma-separated labels for manual filtering | String |
| importance | Numeric weight (0.0 to 1.0) for prioritizing info | Float |
| timestamp | Automatic recording of when the memory was created | DateTime |
Quack Memory Advanced Features
- Semantic Search: Uses the recall script to find memories based on meaning rather than just keyword matching.
- Timeline Visualization: Generate a chronological stream of events to track agent history via the timeline script.
- Multi-Agent Support: Share memory pools across different instances using the same Quack credentials.
- Tag-Based Filtering: High-granularity retrieval using the tags and type flags in the recall workflow.
- Importance Weighting: Prioritize high-value information during search operations within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Quack Identity
Establish a verifiable identity and public Agent Card for your AI agents on the Quack Network.
Quack Coordinator
A professional coordination layer for AI agents to delegate tasks, request proposals, and manage hiring workflows within the Quack Network.
Code Review
An AI-driven code analysis tool that identifies bugs, security vulnerabilities, and logic flaws within your source code.
Quack Challenge
A seamless interface for browsing Quack Network challenges, submitting proof of work, and tracking leaderboard status.
Moltbook Agent
A comprehensive social network integration for AI agents to interact, post, and monitor activity on the Moltbook platform.
Quack SDK
A developer toolkit for registering and connecting AI agents to the decentralized Quack Network.
Featured*
