An open-source Agent development toolkit that integrates the powerful capabilities of Volcengine.

• JDK 17 or above

<dependency>
    <groupId>com.volcengine.veadk</groupId>
    <artifactId>veadk-java</artifactId>
    <version>0.0.1</version>
</dependency>

public class QuickstartAgentExample {
    public static void main(String[] args) {
        // Use an Ark model (replace with a model name available in your Ark Console)
        BaseAgent agent = LlmAgent.builder()
            .name("quickstart-agent")
            .instruction("You are a helpful assistant.")
            .model(new ArkLlm("doubao-seed-1-8-preview-251115"))
            .build();

        Runner runner = new Runner(agent);

        Session session = runner.sessionService()
            .createSession(runner.appName(), "userId", null, "sessionId")
            .blockingGet();

        // Build a simple conversation
        Content userMsg = Content.fromParts(Part.fromText("hello!"));
        RunConfig runConfig = RunConfig.builder().setStreamingMode(RunConfig.StreamingMode.NONE).build();
        Flowable<Event> events = runner.runAsync(session.userId(), session.id(), userMsg, runConfig);

        // Print the final reply
        events.blockingForEach(e -> {
            if (e.finalResponse()) System.out.println(e.stringifyContent());
        });
    }
}

The example project requires the following environment variables before running (an explicit error is thrown if missing):

• MODEL_AGENT_API_KEY: API Key for Volcengine Ark service (used by ArkLlm)

Example setup (macOS / Linux):

export MODEL_AGENT_API_KEY="<your-ark-api-key>"

In the repository root, run: ./mvnw clean -DskipTests package

After building, the compiled artifacts needed by the examples will be generated in example/target.

Entry class: com.volcengine.veadk.example.AgentCliRunner.

Run it (without modifying the POM, directly via Maven Exec plugin coordinates):

./mvnw -pl example -q compile exec:java -Dexec.mainClass=com.volcengine.veadk.example.AgentCliRunner

Interaction notes:

• After startup, follow the prompt to input messages and interact with ArkAgent.
• Type quit to exit.

Start command:

./mvnw -pl example -q compile exec:java \
    -Dexec.mainClass="com.google.adk.web.AdkWebServer" \
    -Dexec.args="--adk.agents.source-dir=example/target --server.port=8000"  

• Access URL: http://localhost:8000

• Import the Maven multi-module project using IntelliJ IDEA or Eclipse.
• Directly run the main method of AgentCliRunner or AdkWeb.
• Ensure the required environment variables are injected in your IDE run configuration (or start the IDE from a shell that has them set).
• If you need web search, Viking Memory, or Viking Knowledgebase, configure these environment variables:
  • VOLCENGINE_ACCESS_KEY: Volcengine AccessKey
  • VOLCENGINE_SECRET_KEY: Volcengine SecretKey
• If you need TLS Trace, besides AK/SK, also configure the TLS topic:
  • OBSERVABILITY_OPENTELEMETRY_TLS_SERVICE_NAME: ID of the TLS service trace log topic

• Python version and documentation: veadk-python.

• Error on startup Missing required configuration: <ENV_NAME>: indicates a required environment variable is not set; please complete it according to the prompt.
• Unable to access memory/knowledgebase/search services: check AK/SK and network connectivity.
• Port occupied: if port 8000 is occupied, adjust via --server.port or in the startup parameters of AdkWeb.main.

This project uses the Apache License 2.0; see the LICENSE file for details.