nativeORT: Native 'R' 'ONNX' Runtime

Provides 'R' native 'ONNX' model inference without requiring 'Python', 'reticulate' bindings, or 'TensorFlow'. This package directly binds the 'ONNX Runtime' C API via 'Rcpp', enabling real-time inference for '.onnx' engines, all within 'R'. Standard CPU execution is supported as well as the 'CoreML' Execution Provider (CEP) for Apple Silicon, all without external bindings. This package handles OS detection, linking 'ONNX' libraries, and inference. For more information about 'ONNX Runtime' see <https://onnxruntime.ai/>.

Version: 0.1.2
Imports: Rcpp, digest, glue
LinkingTo: Rcpp
Suggests: ggplot2, knitr, rmarkdown
Published: 2026-05-12
DOI: 10.32614/CRAN.package.nativeORT (may not be active yet)
Author: Caleb Carr [aut, cre]
Maintainer: Caleb Carr <calebmcarr1 at gmail.com>
BugReports: https://github.com/calebmcarr/nativeORT/issues
License: MIT + file LICENSE
URL: https://github.com/calebmcarr/nativeORT
NeedsCompilation: yes
SystemRequirements: libonnxruntime (>= 1.20)
Language: en-US
Materials: README, NEWS
CRAN checks: nativeORT results

Documentation:

Reference manual: nativeORT.html , nativeORT.pdf
Vignettes: BenchmarkPerformance (source, R code)

Downloads:

Package source: nativeORT_0.1.2.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): nativeORT_0.1.2.tgz, r-oldrel (arm64): nativeORT_0.1.2.tgz, r-release (x86_64): nativeORT_0.1.2.tgz, r-oldrel (x86_64): nativeORT_0.1.2.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=nativeORT to link to this page.