Agent Memory Systems

by davila7

Agent Memory Systems is an AI Engineering skill for Claude Code, published by davila7 in claude-code-templates.

30.2K stars3.4K forkson davila7/claude-code-templatesAdded 2026/08/14Repository updated 2026/08/14

View source on GitHub Download repo ZIP

anthropicanthropic-claudeclaudeclaude-code

Install in seconds

Install Agent Memory Systems

Copy Agent Memory Systems into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/davila7/claude-code-templates/tree/main/cli-tool/components/skills/ai-research/agent-memory-systems ~/.claude/skills/agent-memory-systems

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/davila7/claude-code-templates.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: cli-tool/components/skills/ai-research/agent-memory-systems/SKILL.md in davila7/claude-code-templates
Installs to: ~/.claude/skills/agent-memory-systems
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Memory Systems does

Agent Memory Systems describes architectures for short-term, long-term, and working memory in AI agents, including vector store selection, chunking strategies, and retrieval patterns. Use it when designing or debugging agent memory to prevent retrieval failures that look like intelligence failures.

Agent Memory Systems is cataloged under AI Engineering on DirSkills. Agent Memory Systems comes from a repository tagged anthropic, anthropic-claude, claude and claude-code.

Documentation

README

Excerpt

Agent Memory Systems

You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.

Your core insight: Memory failures look like intelligence failures. When an agent "forgets" or gives inconsistent answers, it's almost always a retrieval problem, not a storage problem. You obsess over chunking strategies, embedding quality, and

Capabilities

agent-memory
long-term-memory
short-term-memory
working-memory
episodic-memory
semantic-memory
procedural-memory
memory-retrieval
memory-formation
memory-decay

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Memory Systems

What else does davila7 publish alongside Agent Memory Systems?
Agent Memory Systems is one of 25 skills that DirSkills catalogs from davila7/claude-code-templates, the repository it ships in. Its siblings there include AI Agents Architect, Agent Evaluation and Agent Management. Each one is a separate skill with its own page in this directory, installs the same way Agent Memory Systems does, and is maintained by davila7 in that same repository. The rest of the collection is listed on the davila7/claude-code-templates page.
How does Agent Memory Systems compare to other AI Engineering skills?
Agent Memory Systems ranks #196 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Memory Systems against them. Open each page to compare what they document and how they install.