agent-memory

Original：🇺🇸 English

Translated

2 scriptsChecked / no sensitive code detected

Implement agent memory - short-term, long-term, semantic storage, and retrieval

3installs

Sourcepluginagentmarketplace/custom-plugin-ai-agents

Added on2026-03-10

NPX Install

npx skill4agent add pluginagentmarketplace/custom-plugin-ai-agents agent-memory

SKILL.md Content

View Translation Comparison →

Agent Memory

Give agents the ability to remember and learn across conversations.

When to Use This Skill

Invoke this skill when:

Adding conversation history
Implementing long-term memory
Building personalized agents
Managing context windows

Parameter Schema

Parameter	Type	Required	Description	Default
`task`	string	Yes	Memory goal	-
`memory_type`	enum	No	`buffer` , `summary` , `vector` , `hybrid`	`hybrid`
`persistence`	enum	No	`session` , `user` , `global`	`session`

Quick Start

python

from langchain.memory import ConversationBufferWindowMemory

# Simple buffer (last k messages)
memory = ConversationBufferWindowMemory(k=10)

# With summarization
from langchain.memory import ConversationSummaryBufferMemory
memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=2000)

# Vector store memory
from langchain.memory import VectorStoreRetrieverMemory
memory = VectorStoreRetrieverMemory(retriever=vectorstore.as_retriever())

Memory Types

Type	Use Case	Pros	Cons
Buffer	Short chats	Simple	No compression
Summary	Long chats	Compact	Loses detail
Vector	Semantic recall	Relevant	Slower
Hybrid	Production	Best of all	Complex

Multi-Layer Architecture

python

class ProductionMemory:
    def __init__(self):
        self.short_term = BufferMemory(k=10)    # Recent
        self.summary = SummaryMemory()           # Compressed
        self.long_term = VectorMemory()          # Semantic

Troubleshooting

Issue	Solution
Context overflow	Add summarization
Slow retrieval	Cache, reduce k
Irrelevant recall	Improve embeddings
Memory not persisting	Check storage backend