memory

Reads long-term memory files to preserve historical context across sessions.

Updated Jan 24, 2026
One-click install
npx skills add https://github.com/maxgent-ai/maxgent-plugin --skill memory-maxgent-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/maxgent-ai/maxgent-plugin/tree/main/skills/memory
Command: npx skills add https://github.com/maxgent-ai/maxgent-plugin --skill memory-maxgent-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Read long-term memory files to access historical context preserved across compacts and prevent memory decay.

Core Features & Use Cases

  • Read specific memory files like errors.md, context.md, and files.md to retrieve critical context.
  • Automatic truncation keeps content within a manageable size, preserving recent information for recall.
  • On-demand memory checks after compaction to recall important details and avoid repeating mistakes.

Quick Start

Run the memory.py script to read the desired memory files, such as errors.md, context.md, or files.md.

Frequently Asked Questions about memory

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

FAQPage Schema
How do I retrieve long-term context across sessions after memory decay?

Recovering historical context after compaction requires reading long-term memory files like errors.md, context.md, and files.md. This prevents memory decay and restores critical historical details for debugging and error analysis.

How do I prevent losing historical context after context compaction?

To prevent losing historical context after compaction, perform an on-demand memory check to recall important details from preserved memory files. This avoids repeating past mistakes and maintains session continuity.

What environment variables do I need to set up long-term memory retrieval?

Setting up long-term memory retrieval requires configuring the MAX_PROJECT_ID and MAX_SESSION_ID environment variables. These variables are necessary to locate the correct memory folder for reading historical context files.

Does long-term memory retrieval apply automatic truncation to file content?

Yes, long-term memory retrieval applies a 15000-character automatic truncation to file content. This keeps content within a manageable size and ensures recent information is preserved for effective recall.

What is the best way to analyze historical errors using memory files?

The best way to analyze historical errors is reading specific memory files like errors.md to retrieve critical debugging context. This on-demand memory check prevents repeating past mistakes across sessions.