이미지: GitHub Blog
Summary
- GitHub has released the GitHub Copilot SDK for Java, distributed as a Maven dependency (1.0.7-preview.1)
- It supports BYOK (Bring Your Own Key), allowing integration with any model provider including OpenAI, Azure, and Anthropic
- A sample real estate lead management agent app was released alongside it, built on Jakarta EE 11 and virtual threads
- 발행
- GitHub Blog, 작성자 Edward Burns, 2026-08-10
- SDK 버전
- com.github:copilot-sdk-java 1.0.7-preview.1 (Maven)
- JDK 요구사항
- JDK 17 또는 25 (25 권장, 가상 스레드 활용)
- Copilot CLI 요구 버전
- 1.0.71 이상
- 예제 앱 런타임
- Open Liberty 26.0.0.5 + Jakarta EE 11 (Faces 4.1, CDI 4.1, WebSocket 2.2)
- 핵심 API
- @CopilotTool 애노테이션으로 도구 정의
- 벤더 중립성
- BYOK 지원 시 Copilot 구독 없이도 사용 가능
Java Code That Becomes an AI Agent
When a real estate inquiry app receives a query like "find a three-bedroom home in London under 800 million won," the server spins up a virtual thread to create an independent Copilot agent. This agent then queries the property database, filters matching listings, and generates a response — all in just a few lines of Java code. This is how the GitHub Copilot SDK for Java, released by GitHub on August 10, actually works.
An SDK That Breaks Framework Lock-in
Until now, enterprise Java developers looking to add AI to their apps had only two paths. Using Langchain4j — a library that abstracts away AI model providers for the Java ecosystem — avoided vendor lock-in but created dependency on Langchain4j itself. Using Spring AI meant conforming to the Spring framework's design patterns.
GitHub describes this new SDK as "truly framework-agnostic." It adds BYOK (Bring Your Own Key) support on top, enabling free connection to OpenAI, Azure, Anthropic, and even OpenAI-compatible endpoints. Notably, developers can use the SDK without a GitHub Copilot subscription simply by supplying their own baseUrl and API key.
Syntax Java Developers Already Know
The SDK leverages tools Java developers already use, including CompletableFuture, annotations, lambdas, and virtual threads. Virtual threads, officially introduced in Java 21, are a lightweight threading model that allows thousands of concurrent requests to be handled with minimal system resources. The core API is the @CopilotTool annotation. Developers familiar with writing @GET REST API endpoints will find it intuitive to define tools that the AI can call.
Jakarta EE is the enterprise standard platform that the Java community has continued to develop after Oracle transferred it over. GitHub built this sample application on Jakarta EE 11, a choice that appears intended to underscore the SDK's framework-independent design philosophy.
Sample App: A Real Estate Lead Pipeline
The released sample application is a real estate lead management agent that receives customer inquiries and automatically matches them to listings. When multiple inquiries are submitted simultaneously, each is processed by a separate Copilot session running in parallel on its own virtual thread. Because the server pushes processing steps to the browser in real time via Jakarta WebSocket, users can watch on screen as the agent calls tools and moves through each stage.
| Component | Technology Used |
|---|---|
| Runtime | Open Liberty 26.0.0.5 |
| Platform | Jakarta EE 11 (Faces 4.1, CDI 4.1, WebSocket 2.2, Data 1.0, Persistence 3.2) |
| UI | PrimeFaces 15.0.16 |
| AI Orchestration | Copilot SDK for Java 1.0.7-preview.1 |
| Database | H2 in-memory (seeded with 10 listings) |
System Requirements and Deployment
The SDK is distributed as a Maven dependency and requires JDK 17 or 25 to run. GitHub recommends version 25, as it allows full use of the latest features, including virtual threads. Prerequisites include Maven 3.9 or higher, a GitHub account with an active Copilot subscription, and Copilot CLI version 1.0.71 or higher.
| Requirement | Value |
|---|---|
| SDK Version | 1.0.7-preview.1 |
| JDK | 17 or 25 (25 recommended) |
| Maven | 3.9 or higher |
| Copilot CLI | 1.0.71 or higher |
What This Actually Changes
Until now, adding AI to Java projects meant committing to a specific ecosystem, whether Langchain4j or Spring AI. This SDK challenges that premise. The key point is that it broadens choice on both the framework side and the model provider side. For enterprises maintaining Java codebases, this opens a path to add AI agent capabilities without disrupting existing CI/CD, build tools, or deployment pipelines. Since it's still in preview, caution is warranted before adopting it in production until the API stabilizes — but for developers already comfortable in the Java ecosystem, the barrier to entry is clearly low, with no separate learning curve required to start experimenting.
