libargus - Zero-allocation native AI runtime for Java 22

Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22)

libargus is a high-performance, model-agnostic inference engine designed for Java 22+ developers. It unifies LLM text generation, speech-to-text, and multimodal vision pipelines into a single, zero-allocation native runtime. Leveraging Project Panama's Foreign Function & Memory API, it eliminates JVM heap overhead and GC pauses by enabling direct, zero-copy memory access to GGML and llama.cpp backends. This solution provides a frictionless, thread-safe C API for orchestrating complex AI tasks like video analysis and real-time transcription with absolute hardware efficiency.

libargus provides a unified, thread-safe C API designed explicitly for frictionless, zero-copy compilation alongside modern unmanaged orchestration frameworks, featuring out-of-the-box structural alignment for the JDK 22+ Project Panama Foreign Function & Memory API.
  1. RandomBK

    I'm curious to hear what bottlenecks you encountered in the traditional path. Of all the compute and data shuffling involved in LLM inference, I would have thought shuffling the raw input/output around would have been a trivial part of the overall cost, and thus not a big optimization target?

  2. hi_hi

    What are the benefits of this. I get the impression it improves speed of…something? Most of the time when using AI comes from the LLM, so I’m curious what this improves?

  3. exabrial

    This is pretty impressive.

More from this day

2026-07-15