Skip to content
CAI
Software that uses CAICheck a score

elixir-nx/ortex

63.2

Adequate · 15 November 2026

1.3k

lines of production code

Rust

with Elixir, Python

5

measurements over time

CAI band scale
CAI trend line
CAI lens gauges

What this system is

Features

Add DistilBERT classification example

Added a new example in the \examples/distilbert\ directory demonstrating how to run a DistilBERT sequence classification model exported to ONNX. The entry includes a Python script (\export.py\) for exporting the \distilbert-base-uncased-finetuned-sst-2-english\ model using Hugging Face transformers and Optimum, an Elixir script (\distilbert\_classification.exs\) for loading the ONNX model and tokenizer to perform inference, and a README explaining the setup and label mapping process.

examples · high confidence

Added Python scripts to export ResNet50 and multi-input models to ONNX with Opset 19

New Python scripts have been added to the repository to facilitate the generation of test models. The \export\_resnet.py\ script exports a pretrained ResNet50 model to ONNX format, while \multi\_input.py\ exports a custom multi-input, multi-output model. Both scripts explicitly target ONNX Opset version 19, ensuring consistent export behavior for downstream testing or integration.

python · high confidence

Initial release of Ortex ONNX Runtime wrapper

This change introduces Ortex, a new Elixir library that wraps ONNX Runtime (via the \ort\ crate) to enable loading and running ONNX models with support for various backends like CUDA and TensorRT. It integrates with Nx.Serving for concurrent and distributed model deployment and includes a storage-only tensor implementation. The release adds the core library code, configuration files (\.formatter.exs\, \.gitignore\), documentation (\README.md\), and sets the initial version to 0.1.10.

(repo-wide) · high confidence

Initial release of Ortex ONNX inference backend

Ortex introduces a new ONNX runtime integration for Elixir, providing an \Nx.Backend\ implementation (\Ortex.Backend\) that allows ONNX models to be used directly with the Nx numerical library. The library includes \Ortex.Model\ for loading and running inference on ONNX files, \Ortex.Serving\ for batched inference via \Nx.Serving\, and native bindings (\Ortex.Native\) that handle ONNX Runtime library loading and tensor operations like slice, reshape, and concatenate. This enables users to leverage pre-trained ONNX models within the Elixir/Nx ecosystem without leaving the language.

lib/ortex · high confidence

Initial release of the Ortex ONNX Runtime backend

This change introduces the Ortex backend, a new native Rust implementation for running ONNX models within Nx. It provides the core infrastructure to load ONNX models, inspect their input/output signatures, and execute inference using the ONNX Runtime (via the \ort\ crate). The backend supports a wide range of tensor data types (including signed/unsigned integers, floats, and bfloat16) and allows users to specify execution providers such as CPU, CUDA, TensorRT, and ROCm. Additionally, it exposes tensor manipulation operations like slicing, reshaping, and concatenation, along with efficient binary serialization for data transfer between the BEAM and the native layer.

native/ortex · high confidence

Introduce Ortex library for ONNX model inference

Added the \Ortex\ module, an Elixir wrapper around ONNX Runtime that allows users to load ONNX models from disk and execute forward passes. The library supports specifying execution providers (such as CPU or CUDA) and graph optimization levels, with default configurations provided for standard usage.

lib · high confidence

Behavioural changes

1 commit (0 fixes) modifying models

A change to existing behaviour in models — 1 commit, 1 file: “added python scripts for generating test models”.

models · low confidence · unverified

Automatic ONNX execution provider selection based on OS

The application now automatically configures the ONNX Runtime backend features based on the operating system to optimize inference performance. On Windows, it enables DirectML; on macOS, it enables CoreML; and on other Unix-like systems, it enables CUDA and TensorRT. This configuration is applied at runtime via the new \config/runtime.exs\ file, ensuring the correct native libraries are loaded without manual intervention.

config · high confidence

Test coverage

Added test coverage for tensor shape operations; Added test suite for data type conversions and model serving.

Dependencies

28 commits updating dependencies (4 manifests)

A dependency / build maintenance change in (dependencies) — 28 commits (5 fixs), 4 files: “Initial commit”; “rustler v0.29.0 for OTP 26 support”; “Allow Nx 1.0”; and 25 more.

(dependencies) · medium confidence · unverified

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Score

  • CAI 57 → 63 (+5.9)
  • Rubric changed (rubric-2026.11.1 → rubric-2026.11.4) — scores are not directly comparable.

Lenses

  • Code Health 99 → 76 (-23.6)
  • Architecture 69 → 69 (+0.0)
  • Maturity 47 → 60 (+12.8)
  • Readiness 51 → 58 (+6.7)
  • Security 95 → 98 (+3.6)

Resolved (6)

  • Orphaned file (lib/ortex/backend.ex)
  • Orphaned file (native/ortex/src/lib.rs)
  • Orphaned file (native/ortex/src/model.rs)
  • Orphaned file (native/ortex/src/tensor.rs)
  • Orphaned file (native/ortex/src/utils.rs)
  • Orphaned files with no living knowledge

New (1)

  • Outdated: nx

Changes since last survey

  • 2 commits — 2 feature/other, 0 fixes

By area

  • (repo) — 2 commits

Notable commits

  • change: Merge pull request #54 from reidmorrison/allow-nx-1.0
  • change: Merge pull request #55 from reidmorrison/ci-pin-rust-1.99

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

elixir-nx/ortex was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 15 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 57039814c49ee6dbc5b6bd41c80e05064e34ce2c — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.73+preprod-52de90b74216.