The AI Framework for Java Applications

Build AI-powered applications in Java with a unified API for any model provider. Supports OpenAI, Gemini, Claude, Bedrock, and 15+ more providers out of the box.

Get Started View on GitHub

Get started with just a few lines of code

import com.google.genkit.Genkit;
import com.google.genkit.plugins.googlegenai.GoogleGenAIPlugin;

Genkit genkit = Genkit.builder()
    .plugin(GoogleGenAIPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("googleai/gemini-3-flash")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

import com.google.genkit.Genkit;
import com.google.genkit.plugins.openai.OpenAIPlugin;

Genkit genkit = Genkit.builder()
    .plugin(OpenAIPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("openai/gpt-5.2")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

import com.google.genkit.Genkit;
import com.google.genkit.plugins.anthropic.AnthropicPlugin;

Genkit genkit = Genkit.builder()
    .plugin(AnthropicPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("anthropic/claude-sonnet-4.6-20260301")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

import com.google.genkit.Genkit;
import com.google.genkit.plugins.xai.XAIPlugin;

Genkit genkit = Genkit.builder()
    .plugin(XAIPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("xai/grok-4-mini")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

import com.google.genkit.Genkit;
import com.google.genkit.plugins.deepseek.DeepSeekPlugin;

Genkit genkit = Genkit.builder()
    .plugin(DeepSeekPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("deepseek/deepseek-v3")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

import com.google.genkit.Genkit;
import com.google.genkit.plugins.ollama.OllamaPlugin;

Genkit genkit = Genkit.builder()
    .plugin(OllamaPlugin.create())
    .build();

String text = genkit.generate(GenerateOptions.builder()
    .model("ollama/gemma3n")
    .prompt("Why is Genkit awesome?")
    .build()).getText();

Simplified AI Integration

The fastest way to build AI features into your Java apps.

Unified APIs for any model

Use Google AI, OpenAI, Claude, Bedrock, and Ollama through one SDK. Switch models with a single line change.

Composable workflows

Structure chat, RAG, tool use, and agents with built-in primitives. Define type-safe flows with input/output schemas.

Production-ready tools

Local dev UI, debugging, tracing with OpenTelemetry, and deployment to Spring Boot, Jetty, or Firebase Cloud Functions.

20+ Plugins

Model providers, vector databases, MCP, evaluators, and server frameworks — all as simple plugin integrations.

Deploy anywhere

import com.google.genkit.plugins.jetty.JettyPlugin;

JettyPlugin jetty = new JettyPlugin(JettyPluginOptions.builder()
    .port(8080).build());

Genkit genkit = Genkit.builder()
    .plugin(GoogleGenAIPlugin.create())
    .plugin(jetty)
    .build();

genkit.defineFlow("tellJoke", String.class, String.class,
    (ctx, topic) -> genkit.generate(GenerateOptions.builder()
        .model("googleai/gemini-3-flash")
        .prompt("Tell a joke about: " + topic)
        .build()).getText());

jetty.start();

import com.google.genkit.plugins.spring.SpringPlugin;

@SpringBootApplication
public class App {
    public static void main(String[] args) {
        SpringPlugin spring = new SpringPlugin();

        Genkit genkit = Genkit.builder()
            .plugin(GoogleGenAIPlugin.create())
            .plugin(spring)
            .build();

        genkit.defineFlow("tellJoke", String.class, String.class,
            (ctx, topic) -> genkit.generate(GenerateOptions.builder()
                .model("googleai/gemini-3-flash")
                .prompt("Tell a joke about: " + topic)
                .build()).getText());

        spring.start(args);
    }
}

import com.google.genkit.plugins.firebase.functions.OnCallGenkit;

public class MyFunction implements HttpFunction {
    private final OnCallGenkit fn;

    public MyFunction() {
        Genkit genkit = Genkit.builder()
            .plugin(GoogleGenAIPlugin.create())
            .plugin(FirebasePlugin.builder().build())
            .build();

        genkit.defineFlow("tellJoke", String.class, String.class,
            (ctx, topic) -> genkit.generate(GenerateOptions.builder()
                .model("googleai/gemini-3-flash")
                .prompt("Tell a joke about: " + topic)
                .build()).getText());

        this.fn = OnCallGenkit.fromFlow(genkit, "tellJoke");
    }

    @Override
    public void service(HttpRequest req, HttpResponse res) throws IOException {
        fn.service(req, res);
    }
}

Build stateful agents

Define server-managed agents with memory, tools, and multi-agent delegation. Persist conversations in the store of your choice.

import com.google.genkit.agent.AgentConfig;
import com.google.genkit.ai.agent.*;

Agent<Map<String, Object>> assistant = genkit.beta().defineAgent(
    AgentConfig.<Map<String, Object>>builder()
        .name("assistant")
        .system("You are a helpful assistant. Remember what the user tells you.")
        .model("googleai/gemini-3-flash")
        .store(sessionStore) // persist sessions in Firestore, DynamoDB, Cosmos DB, PostgreSQL, MongoDB, ...
        .build());

AgentChat<Map<String, Object>> chat = assistant.chat();
chat.send("My name is Ada Lovelace.");
String reply = chat.send("What is my name?").text(); // "Your name is Ada Lovelace."