tessl/maven-dev-langchain4j--langchain4j-agentic

LangChain4j Agentic Framework provides a comprehensive Java library for building multi-agent AI systems with support for workflow orchestration, supervisor agents, planning-based execution, declarative configuration, agent-to-agent communication, and human-in-the-loop workflows.

Overview

Eval results

Files

Getting Started

Name: tessl/maven-dev-langchain4j--langchain4j-agentic
Author: tessl

Installation

Maven:

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-agentic</artifactId>
    <version>1.11.0-beta19</version>
</dependency>

Gradle:

implementation 'dev.langchain4j:langchain4j-agentic:1.11.0-beta19'

Required Dependency

langchain4j-agentic requires langchain4j-core:

<dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j</artifactId>
    <version>1.11.0-beta19</version>
</dependency>

Key Types from langchain4j-core:

dev.langchain4j.model.chat.ChatModel - LLM interface (required)
dev.langchain4j.model.chat.StreamingChatModel - Streaming LLM (optional)
dev.langchain4j.memory.ChatMemory - Chat history storage (optional)
dev.langchain4j.memory.chat.ChatMemoryProvider - Memory provider factory (optional)
dev.langchain4j.rag.content.retriever.ContentRetriever - Content retrieval for RAG (optional)
dev.langchain4j.rag.RetrievalAugmentor - RAG orchestration (optional)
dev.langchain4j.guardrail.InputGuardrail / OutputGuardrail - Safety guardrails (optional)

Essential Imports

import dev.langchain4j.agentic.AgenticServices;
import dev.langchain4j.agentic.Agent;
import dev.langchain4j.agentic.UntypedAgent;
import dev.langchain4j.agentic.agent.AgentBuilder;
import dev.langchain4j.agentic.scope.AgenticScope;
import dev.langchain4j.model.chat.ChatModel;

Simple Agent

// Assuming you have a ChatModel instance from langchain4j-core
// ChatModel chatModel = ...; (e.g., OpenAiChatModel, OllamaChatModel, etc.)

UntypedAgent agent = AgenticServices.agentBuilder()
    .chatModel(chatModel)
    .tools(calculator, weatherService)
    .build();

Object result = agent.invoke("What is 25 * 4 and what's the weather in NYC?");

Declarative Agent

interface Assistant {
    @Agent(name = "assistant", description = "General purpose assistant")
    String assist(String input);
}

Assistant assistant = AgenticServices.createAgenticSystem(Assistant.class, chatModel);
String response = assistant.assist("Hello!");

Next Steps

Common Patterns - Frequently used patterns
Agent Builder API - Complete agent configuration
Workflows - Multi-agent orchestration
Declarative Configuration - Annotation-based agents

Install with Tessl CLI

npx tessl i tessl/maven-dev-langchain4j--langchain4j-agentic@1.11.0