Agent Memory Systems

by davila78da17d671b6fNo license32K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

Instructions onlyAI & Agents
AI-generated overview

Guides the design of agent memory systems, covering memory types, vector stores, chunking and retrieval strategies.

What it does
This skill provides architectural guidance for building memory into AI agents. It covers short-term, long-term and working memory, episodic, semantic and procedural memory, plus memory formation, retrieval and decay. It also presents patterns for choosing memory types, selecting vector stores and chunking documents, along with anti-patterns and sharp-edge cautions. It produces design guidance rather than code or files.
When to use it
Use it when planning or reviewing how an agent should store and retrieve information across interactions. It fits decisions about memory architecture, vector store choice and chunking or retrieval strategy. It is not aimed at writing the implementation code itself.
Requirements
No scripts or tools are required; it is an instructions-only document. Applying its guidance assumes an agent or system with a vector store and embedding model available.

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

Patterns

Memory Type Architecture

Choosing the right memory type for different information

Vector Store Selection Pattern

Choosing the right vector database for your use case

Chunking Strategy Pattern

Breaking documents into retrievable chunks

Anti-Patterns

❌ Store Everything Forever

❌ Chunk Without Testing Retrieval

❌ Single Memory Type for All Data

⚠️ Sharp Edges

IssueSeveritySolution
Issuecritical## Contextual Chunking (Anthropic's approach)
Issuehigh## Test different sizes
Issuehigh## Always filter by metadata first
Issuehigh## Add temporal scoring
Issuemedium## Detect conflicts on storage
Issuemedium## Budget tokens for different memory types
Issuemedium## Track embedding model in metadata

Related Skills

Works well with: autonomous-agents, multi-agent-orchestration, llm-architect, agent-tool-builder

Source and attribution

Source:davila7/claude-code-templatesincli-tool/components/skills/ai-research/agent-memory-systemsat commit8da17d6

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal