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

Quick Start

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

Multi-Layer Architecture

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

Troubleshooting

Best Practices

• Use multi-layer memory for production
• Set token limits to prevent overflow
• Add metadata (timestamps, importance)
• Implement TTL for old memories

Related Skills

• rag-systems – Vector retrieval
• llm-integration – Context management
• ai-agent-basics – Agent architecture

References

• LangChain Memory
• MemGPT Paper