langgraph and langchain

LangGraph is a specialized orchestration framework built on top of LangChain that enables structured, stateful agent workflows through graph-based control flow, making them complementary tools used together rather than alternatives.

langgraph
99
Verified
langchain
98
Verified
Maintenance 25/25
Adoption 25/25
Maturity 25/25
Community 24/25
Maintenance 25/25
Adoption 25/25
Maturity 25/25
Community 23/25
Stars: 26,286
Forks: 4,544
Downloads: 42,304,147
Commits (30d): 145
Language: Python
License: MIT
Stars: 129,354
Forks: 21,296
Downloads: 225,878,213
Commits (30d): 228
Language: Python
License: MIT
No risk flags
No risk flags

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

langchain-ai/langchain

The agent engineering platform

Provides unified abstractions for LLM models, embeddings, vector stores, and retrieval tools across 100+ provider integrations, enabling seamless model swapping and real-time data augmentation. Built on a modular, component-based architecture that supports chains and orchestration patterns, with optional integration to LangGraph for complex agentic workflows and LangSmith for observability and evals.

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