-
What Happens When Nobody Approves the Agent?
Hi! During the live Q&A in the second session of the From Model to Agent: The Agent Framework Harness, Live in C# series on September 10, 2026, someone in the audience asked a practical question: What happens if an agent requests approval, but the user does not answer? Can the approval expire or retry? That question is… â read more
-
The deployment succeeded, but I deployed the wrong agent
Hi! Ok so I spend the full morning with this, so let’s better write it down for Future Bruno: The deployment was green. The hosted agent was active. The Microsoft Foundry Playground could reach it. There were no authentication failures, container crashes, or model errors. There was just one problem: when I asked the C#… â read more
-
Add a Microsoft Foundry model to the GitHub Copilot app
### Display name This is the friendly name displayed by the GitHub Copilot app. It does not have to match the Azure model or deployment name: “`text GPT-5.6-sol on Azure Production reasoning model Foundry GPT-5.6 “` ### Wire model This is the identifier sent in the `model` property of the request. Azure OpenAI routes requests… â read more
-
đ§ MagenticBrain Is Now Supported in ElBruno.LocalLLMs
TL;DR KnownModels.MagenticBrain is now ready for local .NET usage with ElBruno.LocalLLMs. https://huggingface.co/elbruno/MagenticBrain-onnx https://huggingface.co/microsoft/MagenticBrain https://github.com/elbruno/ElBruno.MagenticUI Why this model is important (and what it is designed for) MagenticBrain is not just another general-purpose chat model. It is designed for agent orchestration: planning multi-step tasks, selecting tools, chaining tool calls across rounds, and deciding when to terminate with a final answer. That… â read more
-
đ Fara 1.5-9B Is Now Fully Supported in ElBruno.LocalLLMs
TL;DR Fara1.5-9B now works end-to-end in C# with ElBruno.LocalLLMs. https://huggingface.co/elbruno/Fara1.5-9B-onnx You can run image+text inference locally with LocalVisionChatClient and KnownModels.Fara15_9B. https://github.com/elbruno/ElBruno.MagenticUI When Microsoft Research introduced MagenticLite, MagenticBrain, and Fara1.5, it made a strong case for practical local agentic experiences: Original announcement: https://www.microsoft.com/en-us/research/blog/magenticlite-magenticbrain-fara1-5-an-agentic-experience-optimized-for-small-models/ In plain words: smaller, specialized models can deliver real agentic behavior when the tooling is right. For this repo, that âtooling… â read more
-
I built a weekly AI news digest with GitHub Agentic Workflows. Here is how it works.
This blog post was created with the help of AI tools. I used them to organize ideas and write a first draft, but the workflow, the code, the testing, and the đ¤ enthusiasm are mine. Hi! I like reading AI news. I do not like opening seven tabs, comparing five versions of the same announcement,… â read more
-
Foundry Local Monitor â See every local AI model your machine is running with Foundry Local
Hi! If you have been playing with Foundry Local to run AI models on your own machine, you probably ran into the same thing I did: you never really know what is running. You load a model from the CLI. Your C# app loads another one through the SDK. A Python script spins up its own. A .NET… â read more
-
Run the Right AI Model for the Right Copilot Task â Local or Cloud!
Hi! Part 1 of the CopilotHarness series Big models are great for heavy thinking. But what about simple questions â “rename this variable”, “write a short docstring”, “what does this function do”? Those don’t need GPT-5 across the internet. They can be answered instantly by a model running on your own machine, offline, for free.… â read more
-
Local-first AI Agents in C#: Foundry Local, MEAI, and Microsoft Agent Framework
Hi! If you are building local AI apps in C#, you quickly hit a practical gap: Foundry Local SDK is great for local/on-device inference. Microsoft.Extensions.AI and Microsoft Agent Framework expect an IChatClient. There is no first-party Foundry Local -> IChatClient bridge yet. That is exactly why I created this library Nuget: https://www.nuget.org/packages/ElBruno.MAF.FoundryLocal.Adapter Repo: https://github.com/elbruno/ElBruno.MAF.FoundryLocal/ Sample: ElBruno.MAF.FoundryLocal/src/ElBruno.MAF.FoundryLocal.Console at main ¡ elbruno/ElBruno.MAF.FoundryLocal Why I… â read more
-
GitHub Copilot and tokens: how to keep using AI without burning your budget in three prompts (some personal lessons learned!)
Hi! For a long time, many of us used GitHub Copilot as if it were unlimited magic: autocomplete, chat, agent mode, code review, increasingly powerful models, massive context, and long-running sessions that sometimes felt like a pair-programming marathon. And it worked. Well, mostly. Now, with usage-based billing and AI Credits, many developers are seeing something… â read more
-
Building Cross-Framework Agents with MAF, A2A, NVIDIA NeMo, and Aspire
Hi! What happens when a Python-based AI agent and a .NET-based AI agent need to work together? That is the idea behind MAF-A2A-NVIDIA-NemoAgents (https://github.com/elbruno/MAF-A2A-NVIDIA-NemoAgents-private): a reference app that shows how to combine NVIDIA NeMo Agent Toolkit, Microsoft Agent Framework, Agent-to-Agent communication, and Aspire into one multi-agent workflow. The repo describes itself as a production-ready sample… â read more
-
GitHub Copilot CLI + SQUAD + GPT-5.5 BYOK: Better Engineering, Same Hard Truth
TL;DR This was the final ElBruno.NetAgent experiment: GitHub Copilot CLI + SQUAD using Azure OpenAI GPT-5.5 BYOK against the same app-building challenge I previously tried with CPU-only local models, GPU local models, and GPT-5-mini. The good news: GPT-5.5 was clearly better at staying inside phase boundaries, following safety rules, reducing broad stabilization loops, and working… â read more
-
GitHub Copilot CLI + GPT-5-mini BYOK: The Code Was Cheap, the Quality Gates Were Expensive
The first screenshot shows GitHub Copilot CLI ready with the SQUAD agent and GPT-5-mini selected. Then SQUAD started spawning background agents. â read more
-
From Pet Projects to +20 Open Source NuGet Packages, Thanks to GitHub Copilot đ
Hi! Some of these started as small pet projects. IE: a quick helper for a demo, a tiny tool for a conference, a library to avoid repeating the same code again and again, or one of those âIâll just build this in one eveningâ ideas that somehow becomes a real thing. And now, thanks to… â read more
-
đ Big Update: GPT-Image Models + AI Agent Skills
Hi! Two weeks ago, I shipped t2i â a terminal-first CLI for text-to-image generation. Today I’m excited to announce two major additions that make t2i even more powerful: GPT-Image-1.5 and GPT-Image-2 support â Microsoft’s DALL-E 3 and next-gen models via Azure OpenAI AI agent skill integration â Teach GitHub Copilot and Claude Code to use t2i automatically TL;DR New models: GPT-Image-1.5 (DALL-E 3) and GPT-Image-2 (next-gen) now… â read more
-
đ Meet t2i â The ElBruno.Text2Image CLI
Hi! I just shipped t2i, a terminal-first CLI tool for ElBruno.Text2Image. Generate images from your shell in two commands â no UI, no browser, just a simple cli interface to image generation from the cloud. This is the Lite edition (cloud-only, ~2.4 MB on NuGet) â perfect for CI/CD pipelines, deployment scripts, batch jobs, and developers who live… â read more
-
đźď¸ MAI-Image-2 Just Dropped â And .NET Support Is Already Here
Hi! When Microsoft announced MAI-Image-2, I immediately thought: “I need to add this to ElBruno.Text2Image. Today.” So I did. đ MAI-Image-2 is Microsoft’s new image generation model on Microsoft Foundry â high-quality generation, a synchronous API (no polling!), a 32K character prompt limit, and flexible dimensions. And it’s already supported in ElBruno.Text2Image with the same clean interface you already know. Let me… â read more
-
I Built a .NET 10 Knowledge Graph Builder (Inspired by Karpathy)
Hi! Earlier this year, Andrej Karpathy tweeted about using LLMs as “knowledge compilers” â a mind-bending idea: instead of asking an LLM questions, feed it raw data (papers, code, images) and let it automatically build a structured, navigable knowledge base. No RAG. No vector databases. Just pure understanding compiled into a graph. Then I saw @socialwithaayan showcase graphify â… â read more
-
đ Gemma 4 Is Here â And My C# Library Is (Almost) Ready
Hi! So Google just dropped Gemma 4 â their most capable open model family yet â and I couldn’t resist. I spent a good chunk of time digging into the architecture, trying to convert models, hitting walls, finding workarounds, and hitting more walls. Here’s where things stand with ElBruno.LocalLLMs. Spoiler: the library is ready for Gemma 4. The ONNX runtime…… â read more
-
đ¤ Local LLM Chat Completions in .NET â Just C#
Hi! Let’s look at this code snippet: That’s it. This runs a local LLM. No API keys. No REST calls. The model downloads automatically the first time. Let me show you more. âŹď¸ Download Progress and Model Info When you run a model for the first time, you probably want to see what’s happening. Here’s… â read more
-
Subscribe
Subscribed
Have a WordPress.com account? Log in now.
