penfield-memory

Store persistent agent memory and build knowledge graphs with hybrid BM25, vector, and graph retrieval.

2|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/aztr0nutzs/NET_NiNjA.v1.2 --skill penfield-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: penfield-memory
Source: https://github.com/aztr0nutzs/NET_NiNjA.v1.2/tree/main/skills/skills-folders/penfield
Command: npx skills add https://github.com/aztr0nutzs/NET_NiNjA.v1.2 --skill penfield-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides persistent memory for AI agents, allowing them to store decisions, preferences, and context that survive across sessions, and build knowledge graphs that compound over time.

Core Features & Use Cases

  • Persistent Memory: Store and recall information across agent sessions.
  • Knowledge Graph: Build interconnected knowledge bases for deeper understanding.
  • Hybrid Search: Utilize BM25, vector, and graph search for precise recall.
  • Use Case: An AI assistant can remember your project details, past conversations, and learned preferences, allowing it to provide more personalized and context-aware assistance in future interactions.

Quick Start

Awaken your agent's memory by running penfield_awaken().

Frequently Asked Questions about penfield-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add persistent memory to an AI agent so it remembers context across sessions?

Persistent memory for AI agents allows storing and recalling decisions, preferences, and context across multiple sessions. This Skill enables that retention by running the `penfield_awaken()` function to initialize memory management.

What is the best way to build a knowledge graph for an AI agent that compounds over time?

Building a knowledge graph for an AI agent creates interconnected knowledge bases for deeper understanding. This Skill constructs graphs that compound over time, retaining long-term context and past decisions for future retrieval.

How does hybrid search work for recalling past AI agent decisions and context?

Hybrid search for AI agent memory combines BM25, vector, and graph-based retrieval methods. This approach ensures precise and efficient recall of past decisions, preferences, and contextual information stored during previous interactions.

Can I use this memory Skill with OpenClaw agents for seamless context retention?

Yes, this memory Skill integrates with OpenClaw agents via a dedicated plugin. This integration facilitates seamless memory management, allowing OpenClaw agents to access persistent context and knowledge graphs.

Do I need any external dependencies to enable persistent memory and knowledge graph construction?

No external dependencies are required to enable persistent memory and knowledge graph construction. The Skill operates independently using its internal scripts and references to manage context retention and hybrid search.

Why does my AI agent lose learned preferences and project details between conversations?

AI agents lose learned preferences and project details without persistent memory to store context across sessions. This Skill solves that problem by retaining past conversations and learned preferences for personalized future assistance.