Agent Memory Systems
- 715 installs
- 29.9k repo stars
- Updated July 27, 2026
- davila7/claude-code-templates
agent-memory-systems is a Claude Code skill that designs short-term, long-term, and typed agent memory with chunking, embedding, and retrieval so multi-session agents stay consistent and recall the right facts.
About
agent-memory-systems is a davila7/claude-code-templates skill sourced from vibeship-spawner-skills (Apache 2.0) for architecting agent memory beyond the context window. It covers short-term context-window memory, long-term vector stores, and cognitive patterns that organize storage around retrieval—not just persistence—emphasizing chunking, embedding, and retrieval strategies. Developers reach for agent-memory-systems when agents forget prior sessions, recall irrelevant facts, or need typed long-term memory before production deployment. The skill frames memory as a retrieval problem where stored facts only matter when the right chunk surfaces at the right time.
- Covers short-term (context window), long-term (vector stores), and cognitive memory organization
- Emphasizes retrieval over raw storage: chunking, embeddings, and search quality
- Memory type architecture and vector store selection patterns
- Capability map includes episodic, semantic, procedural, working memory, and memory decay
- Frames agent "forgetting" as retrieval failures, not intelligence limits
Agent Memory Systems by the numbers
- 715 all-time installs (skills.sh)
- +49 installs in the week ending Jul 13, 2026 (Skillselion tracking)
- Ranked #1,386 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Jul 28, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davila7/claude-code-templates --skill agent-memory-systemsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 715 |
|---|---|
| repo stars | ★ 29.9k |
| Security audit | 3 / 3 scanners passed |
| Last updated | July 27, 2026 |
| Repository | davila7/claude-code-templates ↗ |
How do you architect retrieval for agent memory?
Design short-term, long-term, and typed memory with chunking and retrieval so agents stay consistent across sessions.
Who is it for?
Engineers building production agents that must remember users and facts across sessions with reliable retrieval.
Skip if: Simple single-turn chatbots that fit entirely in one context window or teams without vector store infrastructure.
When should I use this skill?
User asks about agent memory design, vector retrieval, chunking embeddings, long-term recall, or fixing agents that forget prior sessions.
What you get
Memory architecture spec covering short-term context, long-term vector store layout, chunking rules, and retrieval strategy.
- memory architecture design
- chunking and retrieval plan
Files
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
| Issue | Severity | Solution |
|---|---|---|
| Issue | critical | ## Contextual Chunking (Anthropic's approach) |
| Issue | high | ## Test different sizes |
| Issue | high | ## Always filter by metadata first |
| Issue | high | ## Add temporal scoring |
| Issue | medium | ## Detect conflicts on storage |
| Issue | medium | ## Budget tokens for different memory types |
| Issue | medium | ## Track embedding model in metadata |
Related Skills
Works well with: autonomous-agents, multi-agent-orchestration, llm-architect, agent-tool-builder
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la462k185k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.379k15.8k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.378k92.5k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.375k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k8FAQ
What memory types does agent-memory-systems cover?
agent-memory-systems covers short-term context-window memory, long-term vector stores, and typed cognitive architectures that organize facts. The skill stresses retrieval quality through chunking, embedding, and search strategies.
Why is retrieval emphasized in agent-memory-systems?
agent-memory-systems treats memory as retrieval, not storage volume. Stored facts only help when chunking and embedding strategies surface the right record at query time, preventing agents from drowning in irrelevant context.
Is Agent Memory Systems safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.