Designing Java code for the agentic development
A Java developer published a four-article series on designing Java code for LLM-based agents like Claude Code, arguing that agent-friendly code makes errors immediately visible to the compiler or inst…
A Java developer published a four-article series on designing Java code for LLM-based agents like Claude Code, arguing that agent-friendly code makes errors immediately visible to the compiler or inst…
OpenAPI documents provide machine-readable contracts that enable AI agents to call HTTP APIs with precise endpoints, parameters, and response formats, replacing guesswork from prose documentation. Fra…
IBM Research introduced ScarfBench, an open benchmark for evaluating AI agents on enterprise Java framework migration tasks across Spring, Jakarta EE, and Quarkus. Tests of frontier coding agents show…
Broadcom announced a major set of security updates for its Spring and Java ecosystems, including the largest release of Spring security patches in the product's history and an extension of clean-room …
Mochallama, a new Java library, enables running llama.cpp inference directly within a Java process using JDK 22's Foreign Function and Memory (FFM) API, eliminating the need for separate daemon proces…
Dan Barrett built OpenProse, a framework that lets developers write programs in structured English and run them with an AI agent like Claude Code. The system uses 'requires' and 'ensures' blocks to wi…
TamboUI, a new Java library for building textual user interfaces (TUIs), launched in response to a call for Java to dominate terminal applications by 2026. Inspired by the Rust-based Ratatui library, …