memory-system-v2

Store and retrieve AI agent memories with semantic search using bash and jq.

Updated Jan 31, 2026

Search Tags:#search #bash #ai agent #memory #persistence #jq

Ready to run

npx skills add https://github.com/dexhunter/Logi-Lobsterism --skill memory-system-v2

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-system-v2
Source: https://github.com/dexhunter/Logi-Lobsterism/tree/main/skills/memory-system-v2
Command: npx skills add https://github.com/dexhunter/Logi-Lobsterism --skill memory-system-v2

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides AI agents with a persistent, fast, and searchable memory, preventing information loss between sessions and enabling recall of past learnings, decisions, and events.

Core Features & Use Cases

Persistent Memory: Stores and retrieves information across different interactions.
Fast Semantic Search: Quickly find relevant memories with sub-20ms search times.
Memory Types: Captures learnings, decisions, insights, events, and interactions.
Use Case: An AI assistant can recall a user's preference from a previous conversation, or remember a complex technical solution it discovered days ago, leading to more coherent and efficient interactions.

Quick Start

Capture a new learning by running the command to capture a memory with its type, importance, and content.

Frequently Asked Questions about memory-system-v2

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 past interactions?▼

Persistent memory for AI agents is achieved through a file-based system that stores and retrieves learnings, decisions, and interactions across sessions. This approach prevents information loss by capturing memories with their type, importance, and content for later recall.

What is the fastest way to implement semantic search for an AI agent memory store?▼

Fast semantic search for an AI memory store can be implemented using bash and jq for efficient, file-based operations. This approach achieves sub-20ms search times, allowing agents to quickly find relevant memories without heavy database dependencies.

Can I store and retrieve AI agent learnings and decisions using only bash and jq?▼

Yes, you can store and retrieve AI agent learnings and decisions using only bash and jq. This Skill is built entirely on these tools for efficient, file-based operation, enabling persistent storage and fast semantic search without requiring external databases.

Does this persistent AI memory system automatically consolidate memories?▼

Yes, this persistent AI memory system features auto-consolidation and importance scoring. It automatically manages the stored learnings, insights, and events, ensuring that the memory remains efficient and relevant for the agent to recall past technical solutions or user preferences.

What are the limitations of using a file-based memory system for AI agents?▼

A file-based memory system for AI agents relies on bash and jq, meaning it operates without a dedicated database server. While it offers sub-20ms search and auto-consolidation, extreme scale or complex relational queries might exceed its file-based design limits.