memory-lite

Organize long-term memory into truth, state, rules, and sources.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/Anthony9906/agent-skills --skill memory-lite
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-lite
Source: https://github.com/Anthony9906/agent-skills/tree/main/memory-lite
Command: npx skills add https://github.com/Anthony9906/agent-skills --skill memory-lite

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill makes long-term memory management lightweight and reliable by organizing memory into truth, state, rules, and sources with a simple workflow that minimizes friction and cognitive load.

Core Features & Use Cases

  • Two-layer memory model: fast core layer for quick context recovery and an extended layer for history, traceability, and deeper notes.
  • Structured memory objects: truth, state, rules, and sources managed separately to keep decisions auditable and reusable.
  • Clear retrieval and update rules: explicit guidance on when to consult memory and how to evolve it after important conversations.
  • Simplicity and maintenance: lightweight notes strategy that emphasizes updating existing core notes rather than creating new ones, with clear separation of concerns.
  • Use case: maintain a living project memory for ongoing work, ensuring decisions, context, and references persist across sessions.

Quick Start

Set up the core memory vault and populate the five core notes according to the memory structure.

Frequently Asked Questions about memory-lite

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

FAQPage Schema
How do I organize long-term memory for AI-assisted workflows in Obsidian?

A two-layer memory model separates quick context recovery in a fast core layer from history, traceability, and deeper notes in an extended layer. This structure keeps decisions auditable and reusable across sessions.

How do I maintain consistent project state and context across AI sessions?

You maintain consistent project state by enforcing clear retrieval and update rules after important conversations. This explicit guidance dictates when to consult memory and how to evolve it without losing prior decisions.

What is the best way to separate truth, state, rules, and sources in knowledge management?

The best way to separate these memory objects is by managing them independently within a structured core notes vault. This enforces separation of concerns, ensuring decisions and references remain auditable.

How do I set up a core memory vault for personal knowledge management?

You set up a core memory vault by populating five core notes according to the memory structure. This lightweight notes strategy emphasizes updating existing core notes rather than creating new ones.

Does this memory workflow require creating new notes for every AI conversation?

No, this memory workflow emphasizes updating existing core notes rather than creating new ones. This lightweight strategy minimizes friction and cognitive load while keeping project memory living and persistent.