A three-layer hierarchical memory system designed to provide AI agents with persistent context across sessions in Portuguese.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memoria-persistente
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 memoria-persistente 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 Memória Persistente?
Memória Persistente solves the fundamental problem of context loss in AI interactions. By implementing a sophisticated three-layer storage architecture, this Openclaw Skills contribution ensures that your agent retains short-term session data, medium-term daily logs, and long-term permanent knowledge.
Developed specifically for the Brazilian community, it provides a structured way to manage information in Portuguese, allowing agents to remember user preferences, complex workflows, and historical data across multiple sessions without losing the thread of the conversation.
Memória Persistente Use Cases
- Preserving user preferences and communication styles across multiple chat sessions.
- Tracking project progress through daily logs that persist for weeks.
- Building a permanent knowledge base of concepts and custom workflows.
- Reducing token usage by offloading long-term data to structured files instead of constant context window stuffing.
How Memória Persistente Works
- The agent captures information during the session and categorizes it based on its projected utility.
- Short-term data is kept in the immediate context for active conversation flow.
- Important events and summaries are written to daily Markdown files for medium-term recall.
- Core facts, tools, and preferences are promoted to the long-term knowledge directory as permanent files.
- The agent queries these directories using specific retrieval commands to re-inject context when needed.
Memória Persistente Setup
To add this capability to your agent, use the following command in your terminal:
clawhub install memoria-persistente
Memória Persistente Data Schema & Taxonomy
The skill organizes data within a hidden .memory/ directory using the following structure:
| Layer | Directory | Description |
|---|---|---|
| Short Term | .memory/context/ |
Stores session.md for the current conversation exchanges. |
| Medium Term | .memory/daily/ |
Contains date-stamped logs (e.g., 2026-03-21.md) for recent history. |
| Long Term | .memory/knowledge/ |
Permanent storage categorized into concepts/, workflows/, preferences/, and tools/. |
Memória Persistente Advanced Features
- Multi-layer retrieval: Search across daily logs or permanent knowledge bases seamlessly.
- Time-based filtering: List recent memories from a specific number of days using the
--diasflag. - Structured categorization: Automatically sorts knowledge into specific sub-folders like preferences or tools for cleaner organization.
- Native Portuguese support: Optimized for processing and storing data in Portuguese for the Brazilian Openclaw Skills ecosystem.
SKILL.md
Loading
Related Openclaw Skills
Pandoc-Docx Converter
A professional document conversion utility for seamless bi-directional translation between Microsoft Word and Markdown formats.
Substack Publishing & Management
A high-performance interface for managing Substack publications directly via REST API and Python, bypassing the need for browser automation.
Consensus
A professional-grade CLI tool designed to analyze consensus operations and evaluate blockchain protocol security.
Tavily Search
A high-performance search skill for AI agents that delivers structured, LLM-ready web data across multiple specialized modes.
Memory System for AI Agents
A local-first tiered memory framework that gives AI agents long-term persistence and session recovery capabilities.
Crawlee Web Scraper
A resilient web scraping engine designed to bypass bot detection and rate limits where standard fetch methods fail.
Featured*
