agent-memory-systems
sickn33/agentic-awesome-skills
Design and implement memory architectures for intelligent agents—short-term context, long-term retrieval, and cognitive organization.
What is agent-memory-systems?
This skill covers the architecture of agent memory systems, including short-term context windows, long-term vector stores, and cognitive frameworks that organize them. Use it when building agents that need to retain and retrieve information across sessions, or when designing memory retrieval strategies for RAG, episodic recall, or semantic knowledge storage.
- Architect short-term memory using context windows
- Design long-term memory with vector stores and embeddings
- Implement chunking and embedding strategies for retrieval
- Organize memory using the CoALA cognitive framework (semantic, episodic, procedural)
- Optimize memory retrieval to ensure stored information is findable and relevant
- Structure conversation history and session persistence
How to install agent-memory-systems
npx skills add https://github.com/sickn33/agentic-awesome-skills --skill agent-memory-systems- Familiarity with vector databases or embedding systems
- Understanding of LLM context windows and token limits
- Basic knowledge of information retrieval concepts
How to use agent-memory-systems
- 1.Read the detailed guide (references/detailed-guide.md) to understand memory architecture patterns and safety requirements
- 2.Identify which memory types your agent needs: semantic (facts), episodic (experiences), or procedural (how-to)
- 3.Design your chunking and embedding strategy based on retrieval requirements
- 4.Implement short-term memory using your LLM's context window
- 5.Set up long-term memory with a vector store and retrieval mechanism
- 6.Validate that your memory system can find relevant information when queried
- 7.Test persistence across sessions and measure retrieval accuracy
Use cases
- Building agents that remember user interactions and preferences across multiple sessions
- Implementing RAG (Retrieval-Augmented Generation) systems with semantic and episodic memory layers
- Designing memory systems for conversational AI that maintains context over long interactions
- Creating knowledge bases where agents can store and retrieve facts, experiences, and procedures
- Optimizing memory retrieval strategies to balance storage capacity with query performance
- AI engineers designing agentic systems
- LLM application developers building stateful agents
- Researchers working on cognitive architectures and memory systems
- Teams implementing RAG or long-term memory for chatbots and assistants
agent-memory-systems FAQ
Short-term memory is the context window of the current interaction—limited but immediately available. Long-term memory uses vector stores and embeddings to persist information across sessions, enabling agents to recall past interactions and knowledge.
A million stored facts are useless if you can't find the right one. Chunking, embedding quality, and retrieval algorithms determine whether your agent actually remembers or effectively forgets.
CoALA is a cognitive architecture that organizes agent memory into three types: semantic memory (facts and knowledge), episodic memory (specific experiences and interactions), and procedural memory (how-to knowledge and skills).
Use it when your task involves agent memory, long-term retention, memory retrieval, vector stores, RAG systems, or designing systems where agents need to remember across sessions.
For long-term memory, yes—vector stores enable semantic search and retrieval. Short-term memory can use the LLM's context window directly, but long-term persistence requires a retrieval mechanism.
Full instructions (SKILL.md)
Source of truth, from sickn33/agentic-awesome-skills.
name: agent-memory-systems description: "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." risk: safe source: vibeship-spawner-skills (Apache 2.0) date_added: 2026-02-27
Agent Memory Systems
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 fragmented with inconsistent terminology. We use the CoALA cognitive architecture framework: semantic memory (facts), episodic memory (experiences), and procedural memory (how-to knowledge).
Detailed Guide
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
When to Use
- User mentions or implies: agent memory
- User mentions or implies: long-term memory
- User mentions or implies: memory systems
- User mentions or implies: remember across sessions
- User mentions or implies: memory retrieval
- User mentions or implies: episodic memory
- User mentions or implies: semantic memory
- User mentions or implies: vector store
- User mentions or implies: rag
- User mentions or implies: langmem
- User mentions or implies: memgpt
- User mentions or implies: conversation history
Example
User request:
Use @agent-memory-systems for this task: Memory is the cornerstone of intelligent agents.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Related skills
More from sickn33/agentic-awesome-skills and the wider catalog.
ai-agents-architect
Design and build autonomous AI agents with tool use, memory systems, planning strategies, and multi-agent orchestration.
ai-engineer
Build production-ready LLM applications, RAG systems, and intelligent agents with vector search and enterprise AI integrations.
api-documentation-generator
Auto-generate comprehensive API documentation from your codebase with endpoints, examples, and best practices.
api-patterns
API design principles for choosing REST, GraphQL, or tRPC and defining response formats, versioning, and pagination.
api-security-best-practices
Implement secure API design patterns: authentication, authorization, input validation, rate limiting, and vulnerability protection.
app-store-optimization
Complete App Store Optimization toolkit for researching, optimizing, and tracking mobile app performance.