para-second-brain

Organize agent knowledge into PARA folders with semantic search.

Updated Jan 31, 2026

Search Tags:#productivity #memory #organization #notes #knowledge-management #para #second-brain

Ready to run

npx skills add https://github.com/dexhunter/Logi-Lobsterism --skill para-second-brain-dexhunter

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: para-second-brain
Source: https://github.com/dexhunter/Logi-Lobsterism/tree/main/skills/para-second-brain
Command: npx skills add https://github.com/dexhunter/Logi-Lobsterism --skill para-second-brain-dexhunter

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of an agent's limited memory and the inability to recall or search across all its stored knowledge, providing a persistent, organized, and searchable knowledge base.

Core Features & Use Cases

PARA Organization: Structures knowledge into Projects, Areas, Resources, and Archive for logical organization.
Full Knowledge Search: Enables semantic search across all notes, not just the immediate memory, via a symbolic link trick.
Session Transcript Indexing: Makes past conversations searchable.
Memory Flush Protocol: Prevents context loss during memory compaction.
Use Case: An agent can now recall specific decisions made days ago, find relevant research material instantly, or retrieve details from past conversations, significantly enhancing its continuity and effectiveness.

Quick Start

Run the setup script to create the PARA directory structure and initialize MEMORY.md.

Frequently Asked Questions about para-second-brain

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

FAQPage Schema

How do I organize my agent's knowledge base using the PARA method?▼

Organize your agent's knowledge base using the PARA method by structuring information into Projects, Areas, Resources, and Archive categories. This logical organization enables full semantic search across local files and ensures persistent, accessible agent memory.

Can an agent search past session transcripts and local notes?▼

Yes, an agent can search past session transcripts and local notes. The Skill indexes session transcripts and implements a symbolic link trick to enable full semantic search across all stored knowledge, not just immediate memory.

How does the memory flush protocol prevent context loss during compaction?▼

The memory flush protocol prevents context loss during compaction by systematically preserving critical information before memory limits are reached. This ensures specific decisions, research materials, and past conversation details remain accessible.

Does this knowledge management Skill require any external dependencies?▼

No, this knowledge management Skill does not require any external dependencies. It operates independently using included scripts and references to structure local files and maintain persistent agent memory without third-party integrations.

What is the best way to give an AI agent persistent memory across sessions?▼

Give an AI agent persistent memory across sessions by indexing local files and session transcripts into a structured PARA directory. This approach enables semantic search and prevents context loss, allowing the agent to recall specific decisions made days ago.

Why does my agent lose context and forget past decisions over time?▼

An agent loses context and forgets past decisions over time due to limited memory capacity and lack of organized storage. Implementing a memory flush protocol and indexing past conversations into a searchable knowledge base solves this continuity problem.