Umbraco.Community.AI.BrowserProvider
1.0.0
dotnet add package Umbraco.Community.AI.BrowserProvider --version 1.0.0
NuGet\Install-Package Umbraco.Community.AI.BrowserProvider -Version 1.0.0
<PackageReference Include="Umbraco.Community.AI.BrowserProvider" Version="1.0.0" />
<PackageVersion Include="Umbraco.Community.AI.BrowserProvider" Version="1.0.0" />
<PackageReference Include="Umbraco.Community.AI.BrowserProvider" />
paket add Umbraco.Community.AI.BrowserProvider --version 1.0.0
#r "nuget: Umbraco.Community.AI.BrowserProvider, 1.0.0"
#:package Umbraco.Community.AI.BrowserProvider@1.0.0
#addin nuget:?package=Umbraco.Community.AI.BrowserProvider&version=1.0.0
#tool nuget:?package=Umbraco.Community.AI.BrowserProvider&version=1.0.0
Browser AI Provider
An experimental community AI provider for Umbraco that runs AI inference entirely in the browser using Chrome's built-in Gemini Nano model. No API keys needed, no cloud costs, and no data leaves the machine.
Note: This package is experimental. Chrome's Prompt API is an early-stage feature and may change between browser updates.
Features
- Chat completions, summarization, and translation using Chrome's Prompt API
- Fully local inference — your data never leaves the browser
- Near-instant job delivery via Umbraco's built-in SignalR infrastructure
- Configurable timeout with optional fallback to another AI provider
- Zero configuration needed beyond enabling Chrome flags
Requirements
- Umbraco 15+ with Umbraco.AI.Core 1.6+
- Chrome 127+ on desktop with the Prompt API enabled
- ~22 GB free disk space for the Gemini Nano model download
- The Umbraco backoffice must be open in Chrome for the provider to work
Getting Started
- Install the package:
dotnet add package Umbraco.Community.AI.BrowserProvider - Register the services in
Program.cs:services.AddBrowserAI(); - Enable Chrome's Prompt API:
- Set
chrome://flags/#prompt-api-for-gemini-nanoto Enabled - Set
chrome://flags/#optimization-guide-on-device-modelto Enabled BypassPerfRequirement - Restart Chrome
- Go to
chrome://componentsand update Optimization Guide On Device Model
- Set
- Open the Umbraco backoffice in Chrome — the provider activates automatically
How It Works
When an AI request is made, the provider queues a job on the server. A SignalR notification is pushed to the backoffice, where a script picks up the job and processes it using Chrome's local Gemini Nano model. The result is posted back to the server and returned to the caller.
For full documentation and configuration options, see the GitHub repository.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- Umbraco.AI.Core (>= 1.6.0)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 1.0.0 | 114 | 4/16/2026 |