# KodeKloud: Beta Courses LangGraph

## LangGraph

### Course Introduction

- [Introduction](https://notes.kodekloud.com/docs/LangGraph/Course-Introduction/Introduction/page.md): Course introducing LangGraph for building stateful, graph-based AI workflows and agents with orchestration, memory, debugging, human-in-the-loop, and hands-on labs.
- [Course Overview and Learning Outcomes](https://notes.kodekloud.com/docs/LangGraph/Course-Introduction/Course-Overview-and-Learning-Outcomes/page.md): Introductory LangGraph course teaching graph-based AI workflows, state management, memory, conditional logic, human-in-the-loop patterns, and observability with hands-on modules and labs.
- [Essential Prerequisites](https://notes.kodekloud.com/docs/LangGraph/Course-Introduction/Essential-Prerequisites/page.md): Overview of practical Python, package, API, and JSON skills needed to start using LangGraph and build model-driven workflows
- [Tool and Environment Preparation](https://notes.kodekloud.com/docs/LangGraph/Course-Introduction/Tool-and-Environment-Preparation/page.md): Guide to preparing a Python development environment for LangGraph, installing dependencies, configuring virtual environments and API keys, and running a quick OpenAI integration test.

### Foundational Graph Concepts and Toolkit Setup

- [LangGraph Introduction](https://notes.kodekloud.com/docs/LangGraph/Foundational-Graph-Concepts-and-Toolkit-Setup/LangGraph-Introduction/page.md): Introduction to LangGraph, a visual declarative state-machine framework built on LangChain for organizing multi-step AI agent workflows with persistent state, branching, retries, and human-in-the-loop support
- [StateGraph Fundamentals](https://notes.kodekloud.com/docs/LangGraph/Foundational-Graph-Concepts-and-Toolkit-Setup/StateGraph-Fundamentals/page.md): Explains StateGraph, a graph-based pattern for building modular workflows where nodes read and update a shared state to compose LLM-driven and human-in-the-loop processes.
- [Demo Simple Orchestration](https://notes.kodekloud.com/docs/LangGraph/Foundational-Graph-Concepts-and-Toolkit-Setup/Demo-Simple-Orchestration/page.md): Minimal tutorial showing how to orchestrate a typed-state LLM call using LangGraph with the OpenAI Responses API

### The Core Workflow: Nodes, Edges, and Routing

- [The Actor Review of LangChain Primitives](https://notes.kodekloud.com/docs/LangGraph/The-Core-Workflow-Nodes-Edges-and-Routing/The-Actor-Review-of-LangChain-Primitives/page.md): Review of LangChain primitives and how LangGraph composes LLMChains tools agents and memory into orchestrated graph nodes and workflows
- [The Path Building Simple Non Cyclical Sequences](https://notes.kodekloud.com/docs/LangGraph/The-Core-Workflow-Nodes-Edges-and-Routing/The-Path-Building-Simple-Non-Cyclical-Sequences/page.md): Guide to building and testing linear non-cyclical LangGraph workflows using shared typed state where nodes return partial updates for deterministic multi-step pipelines
- [The Decision Maker Implementing the Conditional Router](https://notes.kodekloud.com/docs/LangGraph/The-Core-Workflow-Nodes-Edges-and-Routing/The-Decision-Maker-Implementing-the-Conditional-Router/page.md): Explains implementing pure conditional routers in LangGraph that read graph state to route execution based on intent, tool outputs, or signals while keeping decision logic separate from node behavior
- [Practical Application Building a Basic Conversational Agent](https://notes.kodekloud.com/docs/LangGraph/The-Core-Workflow-Nodes-Edges-and-Routing/Practical-Application-Building-a-Basic-Conversational-Agent/page.md): Guide to designing a minimal modular conversational agent in LangGraph using intent classification, conditional routing, optional retrieval, LLM generation, and centralized response formatting.
- [Demo The Conditional Edge](https://notes.kodekloud.com/docs/LangGraph/The-Core-Workflow-Nodes-Edges-and-Routing/Demo-The-Conditional-Edge/page.md): Demonstrates using LangGraph conditional edges to route between web search and direct LLM answers, showing node implementations, state wiring, example runs, and Mermaid visualization

### State Management and Iterative Loops

- [Defining the Graph State Schema](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Defining-the-Graph-State-Schema/page.md): Explains designing and typing a shared graph state schema for LangGraph workflows to improve reliability, observability, and collaboration using Python TypedDicts and best practices.
- [Understanding State Accumulation and Data Flow](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Understanding-State-Accumulation-and-Data-Flow/page.md): Explains how graph-based systems accumulate shared state across nodes to enable contextual reasoning, track execution, support iterative agents, common patterns, and mitigation strategies for state bloat.
- [Implementing State Reducers](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Implementing-State-Reducers/page.md): Explains how LangGraph uses state reducers to control merging, accumulation, and cleanup of shared graph state.
- [Handling Multiple State Schemas](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Handling-Multiple-State-Schemas/page.md): Explains using per‑subgraph state schemas, TypedDicts, adapters, and type guards to make LangGraph workflows modular, reusable, and safe to evolve.
- [Building Cyclical Graphs With Conditional Edges](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Building-Cyclical-Graphs-With-Conditional-Edges/page.md): Shows building a LangGraph workflow that uses conditional edges to route between search and direct answer paths, integrate web search and LLMs, and converge results into a final formatter.
- [Developing Safe Termination Conditions and Loop Limits](https://notes.kodekloud.com/docs/LangGraph/State-Management-and-Iterative-Loops/Developing-Safe-Termination-Conditions-and-Loop-Limits/page.md): Guidance on designing safe loop termination and limits in LangGraph, combining hard iteration counters with semantic goal checks, graceful exits, observability, and logging for reliable flows.

### Context Management and Short-Term Memory

- [Analyzing Token Usage and Context Window Limits](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Analyzing-Token-Usage-and-Context-Window-Limits/page.md): Explains LLM context window limits, token accumulation risks in conversations and workflows, and strategies for measuring and managing prompt size to prevent truncation and maintain coherence.
- [Strategies for Context Overflow](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Strategies-for-Context-Overflow/page.md): Techniques to manage LLM context overflow by prioritizing recent turns, summarizing history, filtering roles, chunking, and using memory snapshots to preserve crucial information and prevent degraded responses
- [Trimming and Filtering Removing Irrelevant Messages](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Trimming-and-Filtering-Removing-Irrelevant-Messages/page.md): Techniques for trimming and filtering conversational context in LLM pipelines to reduce token usage, lower cost, improve latency, and preserve relevant information while avoiding loss of critical context.
- [Implementing a Message Summarization Node](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Implementing-a-Message-Summarization-Node/page.md): Explains building a message summarization node that compresses conversation history to save tokens, manage graph state, trigger summarization, store summaries, and monitor for information loss.
- [Practical Application Building a Chatbot With Summarizing Messages](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Practical-Application-Building-a-Chatbot-With-Summarizing-Messages/page.md): Building a stateful chatbot that summarizes older conversation turns to manage context, reduce tokens, and preserve important facts using hybrid short-term messages and compressed summary
- [Demo The Token Crisis](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Demo-The-Token-Crisis/page.md): Demonstrates periodic summarization to manage conversational token growth, compress older context into summaries, and preserve recent turns to reduce tokens, cost, and latency.
- [Streaming for Responsive UX](https://notes.kodekloud.com/docs/LangGraph/Context-Management-and-Short-Term-Memory/Streaming-for-Responsive-UX/page.md): How streaming LLM outputs token-by-token improves perceived responsiveness, UX, and architecture while detailing handlers, frontend integration, patterns, and production trade-offs.

### Long-Term Memory and Stateful Persistence

- [Stateful Persistence Checkpoints](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/Stateful-Persistence-Checkpoints/page.md): Describes LangGraph's checkpointing to persist workflow runtime state for pause and resume, crash recovery, backend options, security, and production best practices.
- [Managing Concurrency and State Isolation per User Session](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/Managing-Concurrency-and-State-Isolation-per-User-Session/page.md): Guidance on isolating per-user LangGraph executions using unique session identifiers, session-aware state, checkpointing, and concurrency best practices for scalable, auditable multi-tenant systems
- [Architecting Long Term Memory LTM](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/Architecting-Long-Term-Memory-LTM/page.md): Guide to designing long-term memory for conversational agents using vector stores and databases, covering retrieval and write patterns, RAG integration, storage formats, and memory hygiene best practices
- [Leveraging the LangGraph Store](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/Leveraging-the-LangGraph-Store/page.md): Explains LangGraph's persistent store and checkpointing for agent workflows, enabling durable state, pause and resume, observability, and scalable backend options for production deployments.
- [Demo Resuming a Conversation With Persistent Memory](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/Demo-Resuming-a-Conversation-With-Persistent-Memory/page.md): Demonstrates using LangGraph checkpointing to persist and resume conversation state across sessions using a thread identifier and a simple in memory checkpointer
- [LangSmith Observability Introduction](https://notes.kodekloud.com/docs/LangGraph/Long-Term-Memory-and-Stateful-Persistence/LangSmith-Observability-Introduction/page.md): Introduction to LangSmith observability showing how execution traces in LangGraph and LangChain record prompts, tool calls, state changes, errors, and performance for debugging

### Human-in-the-Loop (HILT) Architectures

- [Real Time Interaction and Feedback](https://notes.kodekloud.com/docs/LangGraph/Human-in-the-Loop-HILT-Architectures/Real-Time-Interaction-and-Feedback/page.md): Describes LangGraph human-in-the-loop real time interaction patterns like pause nodes streaming and escape hatches enabling users to guide approve and provide feedback for safer interactive AI workflows
- [Implementing Interruption Points](https://notes.kodekloud.com/docs/LangGraph/Human-in-the-Loop-HILT-Architectures/Implementing-Interruption-Points/page.md): Explains human-in-the-loop interruption points in LangGraph, pausing workflows for human approval, implementation details, examples, front-end integration, and best practices.
- [Designing Human Approval Nodes](https://notes.kodekloud.com/docs/LangGraph/Human-in-the-Loop-HILT-Architectures/Designing-Human-Approval-Nodes/page.md): Designing human approval nodes that pause automated workflows for human review, capture decisions, and route actions to ensure safe, auditable, and controllable automation
- [Demo Breakpoint and Continue](https://notes.kodekloud.com/docs/LangGraph/Human-in-the-Loop-HILT-Architectures/Demo-Breakpoint-and-Continue/page.md): Demonstrates pausing a workflow for human review then resuming execution with preserved workflow state using interrupt and resume primitives

### Advanced Control and Debugging UX

- [Enabling State Editing Mid Execution](https://notes.kodekloud.com/docs/LangGraph/Advanced-Control-and-Debugging-UX/Enabling-State-Editing-Mid-Execution/page.md): How to pause AI workflows to inspect and edit runtime state for debugging, corrections, and supervised overrides with safe interfaces
- [Implementing Dynamic Breakpoints Based on Conditions](https://notes.kodekloud.com/docs/LangGraph/Advanced-Control-and-Debugging-UX/Implementing-Dynamic-Breakpoints-Based-on-Conditions/page.md): Explains using conditional dynamic breakpoints in LangGraph to pause execution for targeted debugging, safety, and operator intervention.
- [The Concept of Time Travel](https://notes.kodekloud.com/docs/LangGraph/Advanced-Control-and-Debugging-UX/The-Concept-of-Time-Travel/page.md): Explains LangGraph's time travel feature using checkpointing to snapshot, restore, and resume graph executions for debugging, rapid iteration, demonstrations, and selective replays.
- [Demo Time Travel with State Injection](https://notes.kodekloud.com/docs/LangGraph/Advanced-Control-and-Debugging-UX/Demo-Time-Travel-with-State-Injection/page.md): Demonstrating workflow checkpointing and state injection to rewind execution, modify checkpoints, and resume for faster debugging, testing, and exploring alternate outcomes

### Conclusion

- [Suggested Self Challenge](https://notes.kodekloud.com/docs/LangGraph/Conclusion/Suggested-Self-Challenge/page.md): A suggested self-challenge to build a LangGraph multi-step assistant emphasizing structured state, human-in-the-loop interruption points, modular nodes, persistence, testing, and sharing for learning and production readiness
- [Next Steps and Resources](https://notes.kodekloud.com/docs/LangGraph/Conclusion/Next-Steps-and-Resources/page.md): Course conclusion offering next steps, project ideas, resources, and practical tips for building stateful LangChain/LangGraph agent workflows with memory, time travel, conditional routing, and community contributions.
- [LangGraph Intermediate Preview](https://notes.kodekloud.com/docs/LangGraph/Conclusion/LangGraph-Intermediate-Preview/page.md): Intermediate guide for scaling LangGraph projects to production with multi-agent orchestration, long-term memory, observability, durability, and human-in-the-loop deployment patterns.
- [Final Word](https://notes.kodekloud.com/docs/LangGraph/Conclusion/Final-Word/page.md): Guide to building robust agentic systems with LangGraph covering graph-based design, memory strategies, observability, human-in-the-loop patterns, state persistence, replay, and community collaboration