#LangGraph
65 related articles
Building a Golden Hour Walk Planner with a 1B Model: Let AI Handle Language, Let Code Handle Math
A local 1B-model walk planner that keeps models on language and code on computation, using LangGraph pipelines and double-bracket place name validation to fight hallucinations. Includes qwen2.5 vs llama3.2 benchmarks, all under 0.5GB RAM.
LangGraph in Production: Five Years of Hard-Won Agent Architecture Experience
A 5-year Agent developer open-sources a production-grade LangGraph reference project, sharing lessons on architecture evolution from conditional trees to graph state machines.
Andrew Ng's Agent Course Highlights: A Practical Path from Single Agents to Full Automation
Key insights from Andrew Ng's AI Agents in LangGraph course: 5 agentic workflow design patterns, building ReAct agents from scratch, LangGraph nodes and state, Agentic Search, persistence, human-in-the-loop, and multi-agent architectures.
Building a Self-Hosted GitLab AI Review Agent with LangGraph.js: Real-World Lessons from Production
A developer's LangGraph.js GitLab AI Agent has reviewed 1,000+ MRs in production with a 2/3 adoption rate. Key lessons: middleware over prompts, Critic filtering, Qwen self-hosting, and per-project memory.
Where Should File Artifacts Live in LangGraph's Pause-and-Resume Workflows?
Where should generated files live in LangGraph pause-resume workflows? This article examines the boundary between graph state and durable output, explaining the immutable revisions + lightweight manifest pattern and a four-layer storage strategy.
Why Do Unattended AI Agents Redo Completed Work? LangGraph's Context Trap
A developer shares how their LangGraph Agent redid completed nodes during unattended runs. Learn why context accumulation — not model drift — is the real culprit, and how active context collapse fixes it.
AI Agent Engineer in Practice: Prompt Injection Defense and LangGraph Production Debugging
A deep technical interview breakdown for AI Agent engineers: LangGraph node/edge design, MCP tool trust models, multi-layer Prompt injection defense, and real production incident diagnosis.
LangGraph 1.0 Hands-On Tutorial: Building Persistent AI Agents from Scratch
A deep dive into the LangGraph 1.0 tutorial series — covering durable execution, memory management, Human in the Loop, and multi-agent systems across six lessons.
Two Years as an AI Agent Engineer: A Real Interview Breakdown on Token Costs, LangGraph, and Production Incidents
A real foundation-tier AI Agent engineer interview breakdown: LangGraph nodes & cost traps, MCP protocol, multi-agent architecture, token cost engineering, and a research agent death-loop incident post-mortem.
From Chain to Graph: Why LangGraph Has Become the Engineering Foundation for AI Applications
Why is the shift from Chain to Graph inevitable? This article breaks down LangGraph's three core elements, compares chain vs. graph across four dimensions, and explains its value as the engineering foundation for AI applications.
LangGraph + MCP + Medical RAG: A Practical Introduction to Enterprise-Grade Multi-Agent Systems
Turing College instructor Loulan breaks down enterprise-grade multi-agent development using LangGraph, LangChain, and MCP through a real medical RAG project.
langgraph-jev: Building Type-Safe Decision Nodes for LangGraph
langgraph-jev wraps TypeSafe's Jev API as typed LangGraph decision nodes, offering typed I/O, confidence scoring, and deterministic routing for reliable AI agent workflows.
New VS Code Extension: Visualize and Debug Your LangGraph Agent Workflows
Agentic Engineering Extension is a VS Code plugin that renders LangGraph and CrewAI agent codebases as interactive graphs, with real execution replay, bidirectional code editing, and built-in evaluation.
LangGraph Agent Memory Staleness: How to Prevent Agents from Making Decisions on Outdated Data
LangGraph persistent memory silently uses stale facts when source data changes. This article breaks down the root cause, compares full rebuild vs TTL vs proactive invalidation, and offers practical engineering solutions.
StateGuard: Adding Transactional Rollback and Audit Capabilities to LangGraph Nodes
StateGuard is an MIT-licensed library that adds transactional rollback, invariant validation, Saga compensation, and audit logging to LangGraph nodes — filling gaps native checkpoints can't address.
How to Intercept LangChain Tool Calls by Argument Without Touching Agent Code
How to intercept LangChain/LangGraph tool calls by argument without modifying agent code. Analyzes a gateway-based policy layer, comparing interrupt() human approval vs. in-tool checks, and key limitations like streaming and fail open.
From Chain to Graph: Why LangGraph Is Essential for AI Application Development
Explore the evolution from Chain to Graph in AI development. Understand LangGraph's nodes, edges, and state, and why graph architecture beats chain-based design for complex Agent applications.
LangGraph Beginner's Guide: The Complete OS for AI Agents
LangGraph is called the OS for AI Agents. This guide covers its relationship with LangChain, State/Node/Edge fundamentals, checkpoints, human-in-the-loop, and subgraphs.
TutorialsFrom Traditional RAG to Agentic RAG: Core Principles and Implementation Guide
Deep dive into the technical differences between traditional RAG and Agentic RAG, covering offline/online pipeline principles, tool-based autonomous decision mechanisms, and a LangGraph-based Agentic RAG implementation via the ChatBox open-source project.
TutorialsAdvanced LangGraph in Practice: Complete Guide to Agent Optimization, Evaluation, and Cloud Deployment
Deep dive into three advanced LangGraph topics: multi-agent architecture optimization, evaluation frameworks for non-deterministic AI systems, and cloud deployment with LangGraph Platform.