elbruno/elbruno.foundrylocalmonitor — explained in plain English
Analysis updated 2026-05-18
Get a Windows notification whenever an app on your machine loads or unloads a local AI model.
Check which processes are currently running Foundry Local and which ports they use.
See which device, such as a GPU or CPU, each loaded model is running on.
Debug a multi-app setup where several programs use Foundry Local at the same time.
| elbruno/elbruno.foundrylocalmonitor | atum-borg-interactive/road-sdk | babelive/windows | |
|---|---|---|---|
| Stars | 2 | 2 | 2 |
| Language | C# | C# | C# |
| Setup difficulty | easy | moderate | moderate |
| Complexity | 2/5 | 3/5 | 3/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Windows only, needs .NET 10 runtime and Foundry Local already installed.
ElBruno.FoundryLocalMonitor is a small Windows tool that lives in the system tray, the row of icons near your clock, and watches Foundry Local, a Microsoft tool that runs AI models on your own computer. Whenever any app on your machine loads or unloads a model through Foundry Local, this monitor shows you a Windows notification about it, no matter what programming language or software kit that app was built with. The tool only works on Windows, since it is built with WPF and relies on the Windows notification area. Beyond the popup notifications, it offers a small always on top status window and a fuller dashboard with three tabs. The Status tab lists every Foundry Local instance found on the machine, showing its web address, process name, port number, and process ID. The Loaded Models tab groups everything by process and shows every model currently loaded into memory, along with a colored badge showing whether it runs on an NVIDIA GPU, another GPU type, or the CPU. The Available Models tab lists every model already downloaded and ready to load. To find all of this, the monitor does not rely only on Foundry's own command line tool. It scans every local network port your computer has open and checks each one to see if it is serving Foundry's model listing API, then groups whatever it finds by process. This lets it detect models loaded through Foundry's command line, through its C# or Python software kits, through a Microsoft tool called .NET Aspire, or through any other app using a different port than usual. You install it with a single command through the dotnet tool system, since it is published as a .NET global tool, and then run it with the command foundrylocalmon. It requires Windows 10 or 11, the .NET 10 runtime, and Foundry Local itself already installed. The project includes sample C# and Python apps used for automated end to end testing, and it can be built from source with standard dotnet restore, build, and test commands. The project is released under the MIT License and made by Bruno Capuano. It credits Foundry Local as the underlying runtime it monitors and a library called Hardcodet.NotifyIcon.Wpf for the tray icon support.
A Windows system tray tool that shows real-time notifications when any app loads or unloads AI models through Foundry Local.
Mainly C#. The stack also includes C#, .NET, WPF.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.