Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

ONNX Runtime in Rust with the ort 2.x crate v1.0.0

Use this resource to run ONNX models locally in Rust with hardware acceleration

New

  • 363 downloads
  • 154 likes
  • 193 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install onnx-runtime-rust-sessions

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent sets up Cargo.toml, creates the session with the right execution provider, links tensors to ndarray and wraps the blocking call for async use. You get Rust code that runs the model, and leads for debugging provider errors.

Mostly picked by

Updated November 2, 2026

Card for the “ONNX Runtime in Rust with the ort 2.x crate” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: Cargo setup, sessions, execution providers and tensors
  • metadata.json: skill metadata

Good fit for

  • An embedding model must run locally inside a Rust application
  • Inference on Apple Silicon must use CoreML

Not for

    Tags

    • rust
    • onnx
    • inference
    • ort

    About

    You say

    “Load this ONNX embedding model in Rust, with CoreML on my Mac.”

    Card for the “ONNX Runtime in Rust with the ort 2.x crate” skill

    Skill published by Claude MPM Team under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to run ONNX models locally in Rust with hardware acceleration
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • metadata.json0.6 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md19.1 KB

    Origin and licence

    Listed unmodified

    Author
    Claude MPM Team
    Source
    github.com/bobmatnyc/claude-mpm-skills/tree/718070a7d622921b01687799a1f9613f36c6f615/toolchains/rust/ml/ort
    Licence
    MIT

    Notice

    « ort » (Claude MPM Team, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.