Backend | Java | Quarkus | AI | Career
The LangChain4j 1.16.0 release notes carry a line that should make anyone running a multi-agent system on the JVM stop scrolling: Introduce Blackboard agentic pattern. Until now, when you wanted agents to coordinate in LangChain4j, you reached for one of the orchestration shapes the library already gave you through AgenticServices: a sequence, a parallel fan-out … Read more
Recently there was a decision in the Java world that left a lot of people unhappy. The OpenJDK maintainers decided they will not accept contributions of AI-generated code. Before we react to it, let’s understand what’s actually going on. When you work on an open source project at the scale of Java, the companies behind … Read more
A multi-step agentic workflow is a stateful process. One agent validates an order, another waits on a human decision, a third finalizes it; each step reads and writes shared state, and the whole run can last seconds, minutes, or days. Anything that runs that long eventually gets interrupted. A deploy rolls the pods. The node … Read more
JobRunr shipped ClawRunr, an open-source Java AI agent that runs on your own hardware and executes scheduled, recurring, and one-off background tasks. The part worth an architect’s attention is where the agent lives: inside the same runtime that already runs those jobs. That placement is the whole story. Most “AI agent for the JVM” pitches … Read more
Quarkus 3.35 ships three optimizations that, stacked together, change the cold-start budget for serverless workloads on Java: build-time JAR tree-shaking, Profile-Guided Optimization for native builds, and Semeru AOT support. Each one targets a different layer. Tree-shaking cuts the classes you ship. PGO improves native code quality. Semeru AOT reduces JVM startup time for teams that … Read more