← Browse tools

Inference & serving

ort

Rust bindings with a higher-level interface for ONNX Runtime and configurable hardware execution providers.

Overview

Research summary

ort is a Rust interface for deploying machine-learning models in ONNX format. It primarily wraps Microsoft ONNX Runtime, giving applications access to model sessions, tensor inputs and outputs, and hardware execution providers. The project also documents alternative pure-Rust runtime backends. Developers can use it for local application inference, edge deployments, or server workloads after exporting a compatible model from another framework. Examples cover several model types, and training support is part of the interface. Its wrapper code is independently maintained from the underlying ONNX Runtime project.

Repository summary

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

ort wrapper code:MITORApache-2.0

Cargo.toml declares alternative licenses. Linked runtimes, execution providers, and deployed model weights retain their own licenses.

Implementation

Recorded implementation details and interfaces for ort.

Implementation details

Rust library wrapping ONNX Runtime, with optional alternative execution backends

Languages
Rust
Repository type
source

Recorded interfaces and capabilities

Licence scope

ort wrapper code:MITORApache-2.0

Cargo.toml declares alternative licenses. Linked runtimes, execution providers, and deployed model weights retain their own licenses.

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

pykeio/ort ↗

Stars
Unavailable
Open issues
Unavailable
Last push
Unavailable
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06

Documentation

Recorded references and research provenance for this entry.

Recorded sources 8

Research metadata

Research date
2026-10-02
Catalogue snapshot
2026-10-06

Community & social 1 channels

Communities