VisioForge.DotNet.Core.AI 2026.7.27

dotnet add package VisioForge.DotNet.Core.AI --version 2026.7.27
                    
NuGet\Install-Package VisioForge.DotNet.Core.AI -Version 2026.7.27
                    
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package.
<PackageReference Include="VisioForge.DotNet.Core.AI" Version="2026.7.27" />
                    
For projects that support PackageReference, copy this XML node into the project file to reference the package.
<PackageVersion Include="VisioForge.DotNet.Core.AI" Version="2026.7.27" />
                    
Directory.Packages.props
<PackageReference Include="VisioForge.DotNet.Core.AI" />
                    
Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package.
paket add VisioForge.DotNet.Core.AI --version 2026.7.27
                    
#r "nuget: VisioForge.DotNet.Core.AI, 2026.7.27"
                    
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package.
#:package VisioForge.DotNet.Core.AI@2026.7.27
                    
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package.
#addin nuget:?package=VisioForge.DotNet.Core.AI&version=2026.7.27
                    
Install as a Cake Addin
#tool nuget:?package=VisioForge.DotNet.Core.AI&version=2026.7.27
                    
Install as a Cake Tool

VisioForge.DotNet.Core.AI information

The ONNX package adds ONNX Runtime based inference blocks for the MediaBlocks pipeline, including a generic ONNX inference block, a YOLO object detector block, object analytics (multi-object tracking, tripwire, polygon zones), an OCR block, and a license plate recognizer block.

Platform support

The package is referenceable from the full SDK framework matrix (.NET Framework 4.6.1+, .NET Core 3.1, and .NET 5 through .NET 10, including the Windows and mobile variants).

At runtime, inference requires an ONNX Runtime native build for the process architecture. ONNX Runtime ships native binaries for win-x64, win-arm64, linux-x64, linux-arm64, osx-arm64, android, and ios. There is no win-x86, osx-x64 (Intel Mac), or linux-musl (Alpine) native build — a 32-bit process, an Intel Mac, or a musl-based Linux container has no native runtime and will fail to load a session. The iOS/Android targets compile, but the YOLO drawing/inference path on mobile is best-effort and not fully tested.

GPU acceleration

On Windows the package uses the DirectML ONNX Runtime build, so inference runs on any DirectX 12 GPU (NVIDIA, AMD, or Intel) with no extra setup. The execution provider defaults to OnnxExecutionProvider.Auto, which selects the fastest backend present in the loaded native build and falls back to the CPU when no GPU is available.

  • Call the static OnnxInferenceEngine.GetAvailableProviders() to detect what is available (for example, it returns DmlExecutionProvider on a Windows DirectX 12 host).
  • Read YOLOObjectDetectorBlock.ActiveProvider (or OnnxInferenceBlock.ActiveProvider) after the block is built to see which provider actually engaged.
  • Set Provider explicitly (CPU, DirectML, CUDA, CoreML) to override the automatic choice. Requesting a provider that is not present logs a warning and transparently falls back to the CPU.

CUDA and CoreML acceleration require the matching ONNX Runtime native build, which is not bundled here; on non-Windows targets the package uses the base CPU build.

Samples

Sample applications are available on GitHub.

Deployment

Several SDKs are available for deployment inside this package. Please check the Help page for more information.

More information

Product Compatible and additional computed target framework versions.
.NET net5.0 is compatible.  net5.0-windows was computed.  net5.0-windows7.0 is compatible.  net6.0 is compatible.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net6.0-windows7.0 is compatible.  net7.0 is compatible.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net7.0-windows7.0 is compatible.  net7.0-windows10.0.19041 is compatible.  net8.0 is compatible.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed.  net8.0-windows7.0 is compatible.  net8.0-windows10.0.19041 is compatible.  net9.0 is compatible.  net9.0-android was computed.  net9.0-android35.0 is compatible.  net9.0-browser was computed.  net9.0-ios was computed.  net9.0-ios18.0 is compatible.  net9.0-maccatalyst was computed.  net9.0-maccatalyst18.0 is compatible.  net9.0-macos was computed.  net9.0-macos15.0 is compatible.  net9.0-tvos was computed.  net9.0-windows was computed.  net9.0-windows7.0 is compatible.  net9.0-windows10.0.19041 is compatible.  net10.0 is compatible.  net10.0-android was computed.  net10.0-android36.0 is compatible.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-ios26.0 is compatible.  net10.0-maccatalyst was computed.  net10.0-maccatalyst26.0 is compatible.  net10.0-macos was computed.  net10.0-macos26.0 is compatible.  net10.0-tvos was computed.  net10.0-windows was computed.  net10.0-windows7.0 is compatible.  net10.0-windows10.0.19041 is compatible. 
.NET Core netcoreapp3.1 is compatible. 
.NET Framework net461 is compatible.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 is compatible.  net48 was computed.  net481 was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (1)

Showing the top 1 NuGet packages that depend on VisioForge.DotNet.Core.AI:

Package Downloads
VisioForge.DotNet.Core.AI.Whisper

VisioForge AI Whisper — local speech-to-text (Whisper ASR + Silero VAD) for live subtitles.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
2026.7.27 42 7/27/2026
2026.7.25 59 7/25/2026
2026.7.24 63 7/23/2026
2026.7.23 67 7/22/2026
2026.7.22 63 7/22/2026
2026.7.21 64 7/21/2026
2026.7.8 116 7/8/2026
2026.7.7 77 7/7/2026
2026.7.6 87 7/6/2026
2026.7.5 80 7/5/2026
2026.7.2 84 7/2/2026
2026.6.28 86 6/28/2026
2026.6.26 84 6/25/2026
2026.6.25 101 6/24/2026

Bug fixes and performance improvements. Please check the changelog.