Getting Started with LM Studio & Agent Framework for .NET Developers

[anktsrkr]

✨ Why This Excites Me

The Microsoft Agent Framework lets you build, orchestrate, and manage multi-agent AI systems with .NET.

Combine it with LM Studio to run open-source LLMs locally while exposing an OpenAI-compatible API. This means you can switch seamlessly between local models and cloud APIs without changing your code.

Key features: pluggable memory, deterministic workflows, dynamic agent orchestration, and enterprise-ready tooling.

🧰 What I Did

1. Set up LM Studio

Installed the desktop app.
Enabled “Power User” mode to expose a local OpenAI-compatible REST API.

2. Created a .NET 10 console app

Added the Microsoft.Agents.AI.OpenAI NuGet package.
Built a simple agent (think “Joker” that tells jokes) using the local model.
Tested both non-streaming and streaming completions—super smooth!

3. Ran & Observed

With LM Studio running, the agent generated jokes locally in real-time.
Streaming output worked seamlessly—like magic in your console!

💡 Big Picture

This stack brings prototyping and production closer than ever. It’s fast, flexible, and reliable—perfect for developers who want local control without sacrificing scalability or integration.

If you’re curious, check out the full guide here: Getting Started with LM Studio & Agent Framework

[AhmedAlbadjiEx]

it's asking for API key:

crit: Microsoft.Extensions.Hosting.Internal.Host[10]
The HostOptions.BackgroundServiceExceptionBehavior is configured to StopHost. A BackgroundService has thrown an unhandled exception, and the IHost instance is stopping. To avoid this behavior, configure this to Ignore; however the BackgroundService will not be restarted.
System.ClientModel.ClientResultException: HTTP 401 (invalid_request_error: invalid_api_key)

  Incorrect API key provided: api-Key. You can find your API key at https://platform.openai.com/account/api-keys.