Libonnx

Visit Tool

libonnx is an Open Source AI Agents & Automation tool that provides a lightweight, portable pure C99 ONNX inference engine. It supports hardware acceleration for embedded devices, enabling efficient deployment of AI models on resource-constrained systems.

Claim this tool

No Views Yet

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is libonnx?

libonnx is a lightweight, portable pure C99 ONNX inference engine specifically designed for embedded devices. It offers hardware acceleration support, making it ideal for deploying AI models on systems with limited resources. The library's .c and .h files can be easily integrated into any project. Users can allocate an ONNX context, load models from files, search for input and output tensors, run the inference engine, and then free the context. It supports ONNX version v1.17.0 with opset 24 and includes tools for converting ONNX models into C arrays for embedded use. The project provides clear compilation instructions, cross-compilation examples, and methods for running tests and examples, such as MNIST handwritten digit prediction.

Best used for

Ideal for developers who need to deploy AI models on resource-constrained embedded devices, leverage hardware acceleration for faster inference, and integrate ONNX models into pure C99 projects. Especially valuable for IoT applications and systems requiring efficient, low-level AI integration.

Common actions

deploy AI models

run ONNX inference

accelerate deep learning

integrate AI into embedded systems

open-sourcelow-code/no-codecollaborationautomated workflowworkflowsdeepfakeface swappinggithub copilot"AI Agents"

Capabilities

Key features

Pure C99
ONNX inference engine
Hardware acceleration
Embedded device support
Model conversion tools
Portable library

Target Audience

developerdata scientist

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What ONNX versions and opsets does libonnx support?

libonnx is based on ONNX version v1.17.0 and supports the newest opset 24. This ensures compatibility with a wide range of modern ONNX models, allowing developers to deploy up-to-date AI solutions on their embedded systems.

How can I convert ONNX models for use with libonnx?

You can use tools like `xxd -i <filename.onnx>` on Linux to convert your ONNX model into an unsigned char array. This array can then be used with the `onnx_context_alloc` function to load the model directly into your C99 project, as demonstrated in the examples.

What are the system requirements for compiling libonnx examples?

To compile and run examples like the MNIST handwritten digit prediction, you may need to install additional libraries. For instance, on Ubuntu, `libsdl2-dev` and `libsdl2-gfx-dev` are required for the GUI-based examples, which can be installed via `apt-get`.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra Chatbots & Conversational AI Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce