langgraph and langchain-langgraph-tutorial

A is the core orchestration framework for building agent workflows as directed graphs, while B is an educational resource that teaches how to use that framework in practice—making them complements rather than alternatives.

langgraph
99
Verified
Maintenance 25/25
Adoption 25/25
Maturity 25/25
Community 24/25
Maintenance 0/25
Adoption 8/25
Maturity 8/25
Community 18/25
Stars: 26,286
Forks: 4,544
Downloads: 42,304,147
Commits (30d): 145
Language: Python
License: MIT
Stars: 52
Forks: 13
Downloads:
Commits (30d): 0
Language: Jupyter Notebook
License:
No risk flags
No License Stale 6m No Package No Dependents

About langgraph

langchain-ai/langgraph

Build resilient language agents as graphs.

Supports durable execution with automatic state persistence across failures, human-in-the-loop interrupts for agent inspection/modification, and comprehensive memory management combining short-term working state with long-term persistence. Built as a low-level orchestration framework inspired by Pregel and Apache Beam, it integrates seamlessly with LangChain ecosystem tools including LangSmith for observability and LangSmith Deployments for production scaling of stateful workflows.

About langchain-langgraph-tutorial

doomL/langchain-langgraph-tutorial

Comprehensive tutorials for LangChain, LangGraph, and LangSmith using Groq LLM. Learn to build advanced AI systems, from basics to production-ready applications. Covers key concepts, real-world examples, and best practices. Ideal for beginners and experts alike. Elevate your AI development skills!

The tutorials progressively build from LangChain fundamentals through LangGraph's state-machine graph architecture, covering agent types (ReAct, zero-shot, plan-and-execute), memory systems, and RAG implementations. It demonstrates practical patterns like integrating Pydantic for structured outputs, combining LangChain components within LangGraph workflows, and implementing production concerns including rate limiting, cost optimization, and monitoring. Real-world applications span content moderation, customer support automation, and semantic search pipelines, all accelerated by Groq's high-performance inference.

Scores updated daily from GitHub, PyPI, and npm data. How scores work