Context Engineering for AI Agents Using LangGraph: Semantic Memory | Step-by-Step
Resources: GitHub: https://github.com/homayounsrp/MCP-Po... The credit for this knowledge goes to this course: https://learn.deeplearning.ai/courses... Previous Videos: Part 2: Building an AI Agent with LangGraph & Neo4j: • Building an AI Agent with LangGraph & Neo... Part 4: Building a Supervised Agentic RAG : • Building Supervised Agentic RAG with LangG... Part 8: Building an Online Learning AI Agent | Non-Technical Explanation: • Context Engineering for AI Agents Using La... In this video, I walk you through real-world context engineering for AI agents using Model Context Protocol (MCP), LangGraph, and a fully implemented semantic memory system. Context engineering is the practice of designing how an AI agent manages information across tools, steps, and sessions. It’s what transforms an LLM from a reactive chatbot into a proactive assistant—one that remembers, adapts, and evolves over time. We start by using MCP as the backbone for structured agent context, ensuring that goals, inputs, outputs, and intermediate states are preserved and shared across multiple components. Then, with LangGraph, we orchestrate multi-step, stateful workflows. Finally, I show you how to implement LangMem’s semantic memory—allowing the agent to persist and retrieve key knowledge from past interactions. This isn’t just theory—you’ll see a working demo of a context-aware agent that retains meaning, recalls user-specific details, and makes smarter, more relevant decisions over time. If you’re serious about building AI systems that scale and actually understand users, then context engineering is the skill to master. And this video will show you how to start doing it, step by step. ----- Timestamps: 0:00 - Intro 1:00 - System Design 2:53 - Implementation 12:44 - Demo 14:38 - Outro LangGraph,MCP,Model Context Protocol,LangGraph tutorial,build AI agent,LangGraph MCP integration,AI agents,LangGraph agents,MCP integration,Using MCP with LangGraph agents,Context Engineering for Agents,Context Engineering — The Hottest Skill in AI Right Now,Context Engineering is the New Vibe Coding (Learn this Now),Context Engineering vs. Prompt Engineering: Guiding LLM Agents,Context Engineering: What It Is and Why It Matters

Don't learn AI Agents without Learning these Fundamentals

Stop Confusing LangChain, LangGraph, and LangSmith | Full Breakdown
![[Highly Recommended] A Deep Dive into 'Orca': The IDE for Multiple AIs—Easily Run Parallel Tasks ...](https://i.ytimg.com/vi/iq5po7h8nYc/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLCpG_PIbMATrtEukgmQUVuyL84Y5A)
[Highly Recommended] A Deep Dive into 'Orca': The IDE for Multiple AIs—Easily Run Parallel Tasks ...

Hybrid RAG: Mastering Context By Combining GraphRAG and VectorRAG using LangGraph, NEO4J & PineCone

I Was Wrong About GraphRAG: Here's What Won in 2026

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

How RAG, GraphRAG, and Context Engineering Improve AI Performance

Build GraphRAG with Neo4j & LangChain

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Hermes Architecture EXPLAINED: Memory, Context & Gateways

The Moment That Changed Software Development!

Building Effective Agents with LangGraph

Is RAG Still Needed? Choosing the Best Approach for LLMs

Context Engineering for AI Agents Using LangGraph: Episodic Memory | Step-by-Step

How to add long-term memory using PostgreSQL to LangGraph ReAct agent🤖: Python — LangGraph #3

Stop Prompting Claude. Use Karpathy's Method Instead.

How AI agents & Claude skills work (Clearly Explained)

Context Engineering for Agents

What AI Agent Skills Are and How They Work

