Embedded local LLM inference via ONNX Runtime — zero external processes, inference runs entirely inside the JVM on CPU, no data leaves the process. Uses platform threads only, so it runs on Java 17+.

Compile Dependencies (7)

Category/LicenseGroup / ArtifactVersionUpdates
Apache 2.0
ai.djl.huggingface » tokenizers
Deep Java Library (DJL) NLP utilities for Huggingface tokenizers
0.31.00.36.0
JSON Lib Apache 2.0
com.fasterxml.jackson.core » jackson-databind2 vulnerabilities
General data-binding functionality for Jackson: works on core streaming API
2.21.43.2.1
MIT
com.microsoft.onnxruntime » onnxruntime
ONNX Runtime is a performance-focused inference engine for ONNX (Open Neural Network Exchange) models.
1.20.01.27.0
MIT
io.github.argonizer » prooopt-core
Annotations, AOP interceptor, autoboxer, function registry, model-router interface, context,
0.1.00.1.1
Logging Apache 2.0
org.apache.logging.log4j » log4j-api
API for Apache Log4J, a highly configurable logging tool that focuses on performance and low garbage generation. It has ...
2.26.02.26.1
Logging Apache 2.0
org.apache.logging.log4j » log4j-core
Implementation for Apache Log4J, a highly configurable logging tool that focuses on performance and low garbage ...
2.26.02.26.1
Config Apache 2.0
org.springframework.boot » spring-boot-autoconfigure(optional)
Spring Boot auto-configuration attempts to automatically configure your Spring application based on the jar dependencies ...
3.5.144.1.0

Test Dependencies (2)

Category/LicenseGroup / ArtifactVersionUpdates
Testing EPL 2.0
org.junit.jupiter » junit-jupiter
Module "junit-jupiter" of JUnit
5.14.46.1.2
Mocking MIT
org.mockito » mockito-core
Mockito mock objects library core API and implementation
5.20.05.23.0