OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Bender

Bender is an MIT-licensed Swift library that provides an abstraction over Apple MetalPerformanceShaders for defining and running neural networks in iOS applications. It can load supported TensorFlow graphs through an adapter that maps operations to Bender layers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Bender — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Bender when building an iOS application that needs to run a neural network and the model’s operations map to the library’s supported layers.

Who it is for

  • iOS developers adding neural-network inference to an application.
  • Developers who want to define networks with Bender layers or import supported TensorFlow models.

Documented uses

  • Define a neural network using layers such as convolution, pooling and fully connected operations.
  • Load a supported TensorFlow model and run it with an input in an iOS app.
  • Explore an image-recognition example using MobileNet.
Before you choose

Requirements & limits

The public repository identifies the library as MIT-licensed and documents CocoaPods and Carthage installation.

  • The TensorFlow adapter covers a subset of operations, so check the supported-layer mapping against the model before relying on import.
  • The README lists Xcode 9 and an iOS 10.0 deployment target.
  • The documented implementation stack is Swift, MetalPerformanceShaders and a TensorFlow model adapter.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add Bender to an iOS project with CocoaPods

Declare the Bender dependency and the documented iOS deployment target in a Podfile.

Before you start

  • An iOS project using CocoaPods.
  • A Podfile.

Steps

  1. Add platform :ios, '10.0' to the Podfile.

  2. Add pod 'MetalBender', '~> 0.5' to the Podfile.

Expected outcome

The Podfile declares MetalBender version range ~> 0.5 and an iOS 10.0 deployment target.

Guide limitations

  • These steps document dependency declaration only; they do not cover building or using a network.
  • The library supports only a subset of TensorFlow operations when importing TensorFlow models.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
xmartlabs/Bender · Official homepage title · retained in its source language
How we review sourcesSuggest a correction