LangGraph

BuildersAgent frameworkLangChain

Library for building stateful, long-running agents as graphs, with persistence and human-in-the-loop.

• Who it's for: people building software and AI agents
• Pricing: Open source; paid LangGraph Platform/LangSmith (verify on the official site)
• Official site: https://www.langchain.com/langgraph
• Source / changelog: https://github.com/langchain-ai/langgraph

Best for / Not for

3 concrete use cases

1. Approval workflow: A graph where the agent drafts, pauses for human approval, then executes.
2. Research agent: Nodes for search, summarize and critique, looping until quality passes.
3. Stateful assistant: Persist conversation state with a checkpointer and resume later.

Pros and cons

How to get started with LangGraph in 10 minutes

1. pip install -U langgraph
2. Follow the official quickstart to build a simple graph
3. Add one tool node
4. Run it and inspect the output
5. Optionally connect LangSmith for traces

Playbooks using LangGraph

• Your first AI agent with the OpenAI Agents SDK in 30 minutes

Comparisons

• LangGraph vs CrewAI

LangGraph alternatives

• OpenAI Agents SDK: Lightweight framework for building multi-agent workflows with tools, handoffs and tracing.
• CrewAI: Python framework for orchestrating role-based teams of agents.
• LangChain: Open-source framework for building LLM apps and agents with integrations.
• LlamaIndex: Framework for building agents and RAG apps over your data; LlamaCloud for parsing.
• AutoGen: Open-source framework from Microsoft for multi-agent applications.
• Pydantic AI: Python agent framework built by the Pydantic team with type-safe outputs.

Recent changes

Weekly updates for LangGraph will be logged here as they appear in issues.

Get changes in your inbox