cONNXr

Pure C ONNX runtime for small embedded devices with zero dependencies.

DecliningOpen SourceLow lock-in

Pricing

Free tier

Flat rate

Adoption

Cooling

License

Open Source

Data freshness

Aging · Jun 8, 2026

Overview

What is cONNXr?

cONNXr is an ONNX runtime written in pure C99, designed to run inference on machine learning models across various frameworks. It's ideal for developers working with constrained hardware due to its minimal footprint and compatibility with older devices.

Key differentiator

cONNXr stands out as a pure C99 implementation with zero dependencies, making it uniquely suited for environments where resource constraints are critical.

Capability profile

Capability Radar

Ease of StartEcosystemValueMaturityFlexibilityScale Ready

Honest assessment

Strengths & Weaknesses

↑ Strengths

Zero dependenciesmedium

Pure C99 implementationmedium

Compatibility with older devicesmedium

ONNX model inference supportmedium

Minimal footprintmedium

↓ Weaknesses

Limited language supporthigh

cONNXr is primarily written in C99 and lacks native bindings or extensive documentation for other languages, making it less accessible to developers not familiar with C.

Complex setup processmedium

The tool requires manual configuration of the ONNX runtime environment which can be error-prone and time-consuming without detailed setup guides.

Performance may degrade with complex modelshigh

While optimized for constrained hardware, cONNXr's performance can suffer when running more complex machine learning models due to its pure C99 implementation and lack of advanced optimization techniques.

Small community and limited supportmedium

Being an open-source project with a niche focus, cONNXr has a relatively small user base which can lead to slower issue resolution and fewer contributions compared to larger projects.

Fit analysis

Who is it for?

✓ Best for

Developers needing to run machine learning inference on devices with very limited resources and no external dependencies

Projects that require a lightweight, standalone ONNX runtime for edge computing tasks

✕ Not a fit for

Applications requiring high-performance GPU acceleration

Environments where the use of external libraries or frameworks is not an issue

Cost structure

Pricing

Free Tier

Available

Open source — free to use

Starts at

$0

Model

Flat rate

Enterprise

None

Performance benchmarks

How Fast Is It?

Ecosystem

Relationships

Next step

Get Started with cONNXr

Step-by-step setup guide with code examples and common gotchas.

View Setup Guide →