A privacy-aware, tiered memory management component for AI agents that secures sensitive data with custom XOR+Base64 encryption and automated cleanup protocols.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install complex-memory-manager
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install complex-memory-manager using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
Complex Memory Manager is a sophisticated, privacy-focused memory framework designed for AI coding agents. Operating as a shared component, it enables multiple skills to maintain cross-session persistent memory while enforcing rigorous data privacy rules. It divides storage into a three-tier model, separating non-sensitive usage metrics from user preferences and private credentials.
By implementing this within your Openclaw Skills workspace, you ensure your agents retain crucial context without risking exposure of private keys, personal identifiable information (PII), or system credentials. It provides the programmatic guardrails needed to make AI workflows both intelligent and secure.
memory/tier1-public/ or memory/tier2-internal/).To integrate this component with your Openclaw Skills, declare it as a dependency in your custom skill's YAML frontmatter:
metadata:
openclaw:
requires:
skills:
- complex-memory-manager
Ensure that the directory structure is initialized in your project workspace:
mkdir -p memory/tier1-public memory/tier2-internal memory/archive
The manager structures memory assets using the following organization:
| Directory / File | Content Type | Format | Encryption |
|---|---|---|---|
memory/tier1-public/ |
Usage stats, common request paths, generic patterns | JSON | None |
memory/tier2-internal/ |
User preferences, custom agent behavioral rules | Markdown Frontmatter | XOR + Base64 |
memory/archive/YYYY-MM/ |
Archival records exceeding 30-day age limit | Markdown/JSON | Retained from tier |
---
tier: internal
source_skill: <skill-name>
key_hint: <skill-name>-<YYYY-MM>
created: <YYYY-MM-DD>
expires: <YYYY-MM-DD>
---
## Encrypted Entry
> <base64-encoded, XOR-encrypted data>
Loading
A Git-backed memory layer and CLI tool that provides durable, version-controlled, and auditable memory for AI coding agents without cluttering your working tree.

An advanced metacognitive engine for structuring complex user requests, selecting and orchestrating subordinate AI skills, and delegating shared concerns.

An automated meta-skill designed to streamline the entire lifecycle of custom AI skill creation, local validation, security scanning, and publishing to ClawHub.

An agent-agnostic tool for converting multi-format documents, spreadsheets, audio files, and web pages into structured Markdown or HTML.

A professional social media analyzer designed to evaluate, score, and optimize Xiaohongshu (RED) post content for maximum platform engagement.

An AI agent skill designed to orchestrate high-performance TLE GPU kernel development, verifier implementations, and automated testing from intake to merge decision.








































