-
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: That is exactly why I created this library Why I created this I wanted a clean, non-REST, in-process integration where: So the library provides a thin adapter: Foundry Local SDK -> FoundryLocalChatClientAdapter -> IChatClient This lets you write provider-agnostic app code while still running local… — read more
-
MAI-Image-2.5 support in ElBruno.Text2Image and the t2i CLI 🚀
Hi! And for the Flash version, use the same generator with the Flash model id: — 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… — 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. — read more
-
🗺️ AOT-Friendly DTO Mapping in .NET
Hi! So, I’ve been away from any scenario that involves and needs data mapping, until I get to OpenClawNet. So I got to the point that I need to map my entities to DTOs? I read this a lot >> runtime reflection doesn’t play nice with AOT and trimming. 😅 So I SQUAD myselft and built: 👉 ElBruno.AotMapper… — read more
-
🖼️ MAI-Image-2 Just Dropped — 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. 😄 MAI-Image-2 is Microsoft’s new image generation model on Microsoft Foundry — 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… — 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” — 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 —… — read more
-
📝 Convert Anything to Markdown in .NET — Meet ElBruno.MarkItDotNet
Hi! You know that feeling when you’re building an AI pipeline or a RAG workflow and you realize: “Wait… I need to turn all these PDFs, Word docs, HTML pages, and random files into something my LLM can actually eat”? 😅 Yeah, me too. That’s exactly why I built: 👉 ElBruno.MarkItDotNet A .NET library that converts files to clean Markdown. Think of… — read more
-
🌟 Gemma 4 Is Here — And My C# Library Is (Almost) Ready
Hi! So Google just dropped Gemma 4 — their most capable open model family yet — 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…… — read more
-
🚀 Build QR Codes in .NET FAST with ElBruno.QRCodeGenerator
Hi! I needed a quick way to generate QR codes in .NET—no heavy dependencies, no complex setup, just something that works and that’s exactly why I built: 👉 ElBruno.QRCodeGenerator An open-source, lightweight library to generate QR codes in multiple formats: 🎬 Watch the video I recorded a quick demo showing how everything works end-to-end 👇… — read more
-
Stop Wasting Tokens: Smart Tool Routing for LLMs with MCPToolRouter
Hi! Today I want to share something that’s been hearing a couple of times: You know when you’re building an AI agent or working with LLMs, and you have dozens (or hundreds) of tools available? What do you do? Send ALL of them to the LLM every single time, right? Yeah, me too. And it’s… — read more
-
🤖 Local LLM Chat Completions in .NET — 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. ⬇️ Download Progress and Model Info When you run a model for the first time, you probably want to see what’s happening. Here’s… — read more
-
🎙️🤖 Real-Time AI Conversations in .NET — Local STT, TTS, VAD and LLM
Hi 👋 What if you could build a real-time voice conversation app in .NET — speech-to-text, text-to-speech, voice activity detection, and LLM responses — all running locally on your machine? That’s exactly what ElBruno.Realtime does. 🎥 Watch the full video here Why I Built This I’ve been building local AI tools for .NET for a while — local embeddings, local TTS with… — read more
-
🎨 Text-to-Image in .NET — FLUX.2 Pro in the Foundry and Stable Diffusion on Your Machine
Hi 👋 These days Microsoft announced FLUX.2 Flex on Microsoft Foundry, I immediately thought: “I need to wrap this for .NET developers.” So I setup a SQUAD team and I did it. And then I thought: “Wait — I have a couple of Test-to-Image local pet projects, what if my SQUAD also help to polish and publish this?… — read more
-
🤖🗣️ Local AI Voices in .NET — VibeVoice & Qwen TTS
Hi! Let’s look at these 2 code snippets… what’s behind them? 🧠 Snippet 1 — VibeVoice (Native TTS in .NET) This generates a WAV file from text using the VibeVoice-Realtime-0.5B model, running locally via ONNX.The first time you run it, the model is automatically downloaded. No REST calls. No API keys. No cloud dependency. 🧠… — read more
-
Microsoft Agent Framework is Release Candidate! Let’s Go 🔥🤖
Hi! Big milestone these days: The Microsoft Agent Framework (MAF) just reached Release Candidate status 🎉 Official announcement here:👉 https://devblogs.microsoft.com/foundry/microsoft-agent-framework-reaches-release-candidate/ As someone who has been building apps, samples, demos, orchestration experiments and livestream content around MAF for months… this one feels GOOD. Let’s talk about this. 🤖 What is Microsoft Agent Framework? The Microsoft Agent… — read more
-
🧠 Building RAG in .NET with Local Embeddings — 3 Approaches, Zero Cloud Calls
Hi! 👋 One of the questions I get most often is: “Bruno, can I build a RAG (Retrieval-Augmented Generation) app in .NET without sending my data to the cloud?” The answer is a resounding YES. 🚀 In this post, I’ll walk you through three different ways to build RAG applications using ElBruno.LocalEmbeddings — a .NET library that generates text embeddings locally using ONNX… — read more