Back to AI Engineering Mind Map
中文·English
🤖 AI EngineeringID: agent-memory-architecture

Agent Memory Architecture

Agent 长短期记忆工程
🎯Core Definition
Agent Memory Architecture is the multi-tiered persistence subsystem that endows stateless LLMs with cross-session personalization, long-term fact retention, and evolving skill accumulation; it structures memory into 3 layers: 1) Working/Short-term Memory (the active conversational Context Window managed via sliding summaries); 2) Long-term Episodic & Entity Memory (vector databases and knowledge graphs storing extracted entities and historical episodic events, e.g., Mem0, Zep); 3) Procedural Memory (reusable executable code snippets, tool blueprints, and verified Reflexion rules).
💡Use Cases
Long-term personalized companion agents, continuously learning software engineering agents (Claude Code, Open-Devin), and multi-month enterprise advisors.
Key Problems Solved
Base LLMs lose all memory upon session reset, while blindly dumping full chat history triggers context window overflow and attention degradation; memory engineering enables selective extraction, decay, contradiction resolution, and precision recall.
🎯5 High-Frequency Exam Points
1
Detail the workflow in Mem0 for dynamically extracting facts, updating existing memories, and invalidating contradictory stale facts?
2
Explain short-term working memory management combining sliding message windows with asynchronous incremental LLM summarization?
3
Derive the tripartite retrieval scoring formula for Episodic Memory: Semantic Similarity + Time Decay Factor + Importance Weight?
4
How does Procedural Memory persist successfully authored Python tool scripts into a dynamic skill library (e.g., Voyager paradigm)?
5
How to implement deterministic hard-deletion across vector/graph memory systems to comply with GDPR 'Right to be Forgotten' mandates?
📖 In-depth Guide:📄 agent-design-patterns
Updated 2026-08-14
🎯
Test Your Knowledge: Practice Questions for "Agent Memory Architecture"
Single choice pitfall questions with instant feedback and mistake tracking.
🚀 Start Card Practice
Previous CardSupervisor-Worker ArchitectureNext CardComputer Use GUI Agent

🔗 More AI Engineering Knowledge Cards

Vector Distance Metrics & L2 NormalizationScalar Quantization (SQ8/SQ4)Product Quantization (PQ)ADC Asymmetric Distance Computation