Progressive Memory

Organize AI agent memory into scannable indexes with token estimations.

26|5|Updated Feb 19, 2026

Search Tags:#context management #information retrieval #ai agent #memory #token efficiency #progressive disclosure

Ready to run

npx skills add https://github.com/kunwl123456/zeroclaw-skills-collection --skill progressive-memory

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Progressive Memory
Source: https://github.com/kunwl123456/zeroclaw-skills-collection/tree/main/progressive-memory
Command: npx skills add https://github.com/kunwl123456/zeroclaw-skills-collection --skill progressive-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill addresses the issue of limited context windows in AI agents by providing a token-efficient memory system that prioritizes relevant information and reduces wasted attention.

Core Features & Use Cases

Token Efficiency: Significantly reduces token usage by scanning an index first and fetching details on demand, rather than loading entire memory dumps.
Structured Memory: Organizes memory into daily files and a long-term memory file, each with a scannable index and detailed entries.
Observation Types: Utilizes icons to categorize memory entries (e.g., rules, pitfalls, fixes, discoveries), enabling faster visual recognition.
Use Case: An AI agent can quickly review its past decisions and learnings by scanning a concise index, only retrieving full details for entries directly relevant to its current task, thus saving processing time and cost.

Quick Start

Use the progressive memory skill to add a new rule to the long-term memory.

Frequently Asked Questions about Progressive Memory

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

FAQPage Schema

How do I reduce token consumption for AI agent memory retrieval?▼

Reduce token consumption by implementing progressive disclosure, which scans a categorized memory index first and fetches full entry details on demand. This prevents loading entire memory dumps into the context window, prioritizing relevant information to save processing time and cost.

What is progressive disclosure in AI agent context management?▼

Progressive disclosure is a context management technique that organizes memory into scannable indexes with token estimations. An AI agent reviews the concise index first, retrieving full details only for entries relevant to its current task, significantly reducing wasted attention.

How do I structure long-term memory files for an AI agent?▼

Structure long-term memory files by organizing entries into daily files and a long-term memory file. Each file contains a scannable index and detailed entries categorized by observation types, such as rules, pitfalls, fixes, and discoveries, enabling faster visual recognition.

How do I categorize AI agent observations for faster context retrieval?▼

Categorize AI agent observations by utilizing specific icons to classify memory entries. This structured memory approach organizes entries into types like rules, pitfalls, fixes, and discoveries, enabling faster visual recognition and efficient on-demand fetching.

Does progressive memory require external dependencies to manage context windows?▼

Progressive memory requires no external dependencies to manage context windows. It is a standalone token-efficient memory system that organizes daily and long-term memory internally using scannable indexes and categorized observation types.