Catniff provides JavaScript developers with a Torch-like deep learning framework.
Open source
24 alternativescONNXr
The cONNXr project provides a pure C runtime for ONNX models intended for embedded devices.
About cONNXr
cONNXr is a runtime for running inference on ONNX machine learning models. It is written in pure C99 with no external dependencies and is aimed at embedded devices and older hardware that cannot compile newer C or C++ code. Models can be trained in any framework that exports to ONNX, such as TensorFlow, Keras, or scikit-learn, and then run with this runtime.
The runtime uses single-threaded C99 code and has no GPU or hardware accelerator support. Several models are supported out of the box, including MNIST, tiny YOLO v2, super resolution, and MobileNet v2. A model that uses an operator the project has not yet implemented will not run. The project describes itself as at a very early stage and not production ready, and it is looking for developers to contribute. Linking it as a static library is not yet supported.
Key features
- Pure C99 ONNX runtime with no external dependencies
- Runs inference on ONNX models exported from frameworks such as TensorFlow, Keras, and scikit-learn
- Command-line runner that takes an ONNX model and a .pb input file
- Example C code showing how to resolve operators and run inference
- Architecture that allows operators to be replaced for bare-metal hardware with dedicated accelerators
- Out-of-the-box support for MNIST, tiny YOLO v2, super resolution, and MobileNet v2 models
Best for: Developers who need to run ONNX model inference on embedded or older hardware that cannot build newer C++ code.
Good for
- Has zero dependencies and is written in pure C99
- Works with models trained in any framework that exports to ONNX
Watch out for
- Described by the project as at a very early stage and not production ready
- Has no GPU or hardware accelerator support and uses non-multi-threaded code
- Models that use operators not yet implemented will not work
cONNXr at a glance
- Website
- github.com/alrevuelta/cONNXr
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
cONNXr alternatives
Tools and sites you could use instead, ranked by how closely they match.
Kubeflow provides a machine learning toolkit for deploying workflows on Kubernetes.
Open source
24 alternatives
Build machine learning applications with Delta, an open-source framework implemented in Rust.
Open source
24 alternatives
MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.
Caffe provides an open framework for building and running deep learning models.
ONNX-MLIR compiles ONNX models using MLIR compiler infrastructure for model deployment workflows.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
cONNXr FAQ
Does cONNXr support GPUs or hardware accelerators?
No. The project states that it has no GPUs or hardware accelerators and uses only pure, non-multi-thread C99 code.
Why might my ONNX model fail to run?
The project says a model that does not work is probably using an operator that has not been implemented yet. Users are invited to open an issue.
Can cONNXr be used as a static library?
Not yet. The project says linking it as a static library is not supported at this time, so the source files must be included and compiled in your project.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.