30 runnable Jupyter notebooks that thoroughly cover LLM agent memory techniques from short-term to long-term, from simple to production-grade. https://github.com/NirDiamant/Agent_Memory_Techniques… This repository breaks down LLM agent memory into six directions: how to manage short-term context, how to store long-term information, how to build cognitive architectures, how to select retrieval routing, how to use existing frameworks, and how to evaluate and deploy. Each direction has a runnable notebook, from the most basic conversation buffer to MemGPT self-editing memory, Zep temporal knowledge graphs, Graphiti episodic-to-semantic extraction — all with code. It also covers Anthropic’s seven-layer memory definition and Mem0’s managed memory layer. Additionally, it includes a decision tree and comparison table for quick reference when you’re unsure which technique to use.

NirDiamant/Agent_Memory_Techniques

Source: https://github.com/NirDiamant/Agent_Memory_Techniques

🧠 Agent Memory Techniques

Learn every agent memory technique for LLM agents.

⭐ If you find this useful, please star the repo so more learners can discover it. 🧭 New here? Start with 01 Conversation Buffer Memory or pick a Learning Path. Prefer a visual? See the Decision Tree below.

30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, working memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production memory patterns.

📖 The RAG Techniques Book is HERE (https://europe-west1-rag-techniques-views-tracker.cloudfunctions.net/rag-techniques-tracker?notebook=agent-memory-techniques–readme&click=book-buy-amazon-title&target=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0D76734SZ%3Ftag%3Ddiamantai-amt-20&text=The%20RAG%20Techniques%20Book%20is%20HERE)

From the same author

#1 Best Seller on Amazon in Generative AI Want to go deeper on RAG (Retrieval-Augmented Generation, the technique of giving a model extra documents so it can answer better)? The book is the long version. You’ll get the intuition behind every technique. You’ll get side-by-side comparisons that show when each one wins and when it quietly fails. You’ll get illustrations that make the tricky parts click.

⏳ Launch window only: $0.99

The price goes up once the launch window closes. Readers who grab it now lock in the lowest price it will ever have.

👉 Get the book on Amazon before the price changes (https://europe-west1-rag-techniques-views-tracker.cloudfunctions.net/rag-techniques-tracker?notebook=agent-memory-techniques–readme&click=book-buy-amazon-cta&target=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0D76734SZ%3Ftag%3Ddiamantai-amt-20&text=Get%20the%20book%20on%20Amazon%20before%20the%20price%20changes)

📫 Stay Updated

🚀WeeklyUpdates 💡ExpertInsights 🎯Top 0.1%Content Join over 50,000 readers getting clear AI tutorials every week. Subscribers also get early access and a 33% discount on my book.

🗺️ Taxonomy of Agent Memory Techniques

The 30 techniques fall into six families. Each family solves a different memory problem. Each technique lives in its own notebook.

📐 Compare Techniques at a Glance

Looking to filter by constraint (persistence, retrieval style, token cost, best-for use case)? See the side-by-side comparison matrix covering all 30 techniques in one table.

📚 All 30 Techniques

🔄 Short-Term Memory (Techniques 1-5)

Manage the conversation inside a single chat.

💾 Long-Term Memory (Techniques 6-11)

Storage that survives across sessions and users.

🧩 Cognitive Architectures (Techniques 12-19)

Patterns borrowed from how humans remember.

🔍 Retrieval & Multi-Agent (Techniques 20-23)

How agents find and share memories.