Type: Practice / Framework
Dependencies: None (markdown only)
Description
A structured memory system for AI agents. Prevents the "forgot how to do things" problem by separating memory into episodic (what happened), semantic (what I know), and procedural (how to do things) layers.
Add memory loading to your wake routine (AGENTS.md)
Use templates when logging events, creating procedures, tracking feedback
Files
File
Purpose
README.md
Full documentation
templates/ARCHITECTURE.md
Memory system overview (copy to memory/)
templates/feedback.md
Success/failure tracking template
templates/procedure-template.md
How-to document template
templates/daily-template.md
Daily log template
templates/compaction-survival.md
NEW: Pre-compaction flush guide
templates/context-snapshot-template.md
NEW: Quick context save template
helpers/check-compaction.sh
NEW: Token limit checker
Key Concepts
Episodic memory: Daily logs of WHAT happened
Semantic memory: Curated knowledge (MEMORY.md)
Procedural memory: HOW to do things
Feedback loops: Learn from success/failure
The Rule
Always capture the HOW, not just the WHAT. Future-you needs the steps.
1---2name: agent-memory-kit3description: Agent Memory Kit4---5# Agent Memory Kit67**Type:** Practice / Framework8**Dependencies:** None (markdown only)910---1112## Description1314A structured memory system for AI agents. Prevents the "forgot how to do things" problem by separating memory into episodic (what happened), semantic (what I know), and procedural (how to do things) layers.1516## Installation1718```bash19# Create memory folder structure20mkdir -p memory/procedures2122# Copy templates23cp templates/ARCHITECTURE.md memory/24cp templates/feedback.md memory/25cp templates/procedure-template.md memory/procedures/26```2728## Usage29301. Read `README.md` to understand the system312. Add memory loading to your wake routine (AGENTS.md)323. Use templates when logging events, creating procedures, tracking feedback3334## Files3536| File | Purpose |37|------|---------|38| `README.md` | Full documentation |39| `templates/ARCHITECTURE.md` | Memory system overview (copy to memory/) |40| `templates/feedback.md` | Success/failure tracking template |41| `templates/procedure-template.md` | How-to document template |42| `templates/daily-template.md` | Daily log template |43| `templates/compaction-survival.md` | **NEW:** Pre-compaction flush guide |44| `templates/context-snapshot-template.md` | **NEW:** Quick context save template |45| `helpers/check-compaction.sh` | **NEW:** Token limit checker |4647## Key Concepts4849- **Episodic memory:** Daily logs of WHAT happened50- **Semantic memory:** Curated knowledge (MEMORY.md)51- **Procedural memory:** HOW to do things52- **Feedback loops:** Learn from success/failure5354## The Rule5556Always capture the **HOW**, not just the WHAT. Future-you needs the steps.
Run npx skillmds@latest add demerzels-lab/agent-memory-kit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Agent Memory Kit It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Demerzels-lab (@demerzels-lab) published this skill. Their other Agent Skills are listed on their SkillMD profile.
Demerzels-lab