Skip to content

🦜🕸️ Welcome to LangGraph4j ( AI Agentic workflow in Java )

License: MIT docs Static Badge Maven Centraldiscord

LangGraph for Java. A library for building stateful, multi-agents applications with LLMs, built for work with Langchain4j and Spring AI

It is inspired by LangGraph solution, part of LangChain AI project.

LangGraph4j is a flexible, powerful orchestration framework built for Java developers working with LangChain4j. It helps you build intelligent applications using AI workflows, graphs, and multi-agent systems with ease.

Features

At macro level these are the features that support the framework:

  • StateGraph: Nodes, Edges (conditional and normal), Entry Points, State Schema

  • Async & Streaming support (via CompletableFuture, Java-async-generator)

  • Checkpoints (save, replay), Breakpoints (pause/resume)

  • Visualization, Interaction, and Debugging using Studio Web App integrated with: Spring Boot, Quarkus & Jetty

  • Graph visualization (PlantUML, Mermaid)

  • Multi-agent support, threads, sub-graphs, and parallel node execution

  • Integrations: Langchain4j, Spring AI,

  • Visual builder (LangGraph4j Builder)

LangGraph4j is a complete solution for building LLM workflows in Java:

  • Visual + Code = Clarity

  • Async + Graph = Scalability

  • Checkpoints + Studio = Debug-friendly

  • Agents + Integration = Power

For more details please see Features