[HN Gopher] Microsoft Agent Framework
___________________________________________________________________
Microsoft Agent Framework
Author : mooreds
Score : 42 points
Date : 2025-12-24 17:41 UTC (5 hours ago)
(HTM) web link (learn.microsoft.com)
(TXT) w3m dump (learn.microsoft.com)
| randv wrote:
| nice, are there other frameworks that are similar or better?
| sroussey wrote:
| Certainly not better... it's a one person project after all...
| but I have a workflow in typescript solution, not quite ready
| for prime time at workglow.dev. I'll have AI agent stuff both
| in the framework and the UI (it's feature flagged off at the
| moment) in January/February time frame.
|
| The site above only runs local in browser models and uses a
| local user account. So it's easy for infinite people to play
| with and costs me nothing to host.
|
| It's still a ways away from a Show HN post, and is more capable
| with remote frontier models, or with gguf over onnx (maybe?)
| whenever I get the local app out.
| somedumbguy22 wrote:
| I use Google's Agent Development Kit (adk)[0] at work and enjoy
| using it quite a bit.
|
| [0]: https://google.github.io/adk-docs/
| mooreds wrote:
| I have a friend who works at Mastra[0].
|
| Got part way through their tutorial, seemed okay. Haven't used
| it in prod, though.
|
| 0: https://mastra.ai/
| linkage wrote:
| TanStack AI is open source and almost ready for production:
| https://tanstack.com/ai/latest
| lumost wrote:
| Curious what people see in these frameworks in 202(6). My
| experience has been that an agent is a simple while loop over
| tools/instructions/dialog. More complex integrations generally
| lie in the tools/context retrieval - but those have so far been
| so domain specific that it's not worth pulling in a framework.
| diwu1989 wrote:
| OpenAI agent sdk makes it extremely simple to get started with
| function calling and subagent-as-tools delegations.
|
| If you use it with OpenAI responses api, there's not even any
| need to store input items in your own DB
| dmos62 wrote:
| > Agent Framework offers two primary categories of
| capabilities:
|
| > AI agents: Individual agents that use LLMs to process user
| inputs, call tools and MCP servers to perform actions, and
| generate responses. Agents support model providers including
| Azure OpenAI, OpenAI, and Azure AI.
|
| > Workflows: Graph-based workflows that connect multiple agents
| and functions to perform complex, multi-step tasks. Workflows
| support type-based routing, nesting, checkpointing, and
| request/response patterns for human-in-the-loop scenarios.
| campbel wrote:
| Anything beyond this is usually a play to trap you into an
| ecosystem. No reason to adopt any of these frameworks,
| especially if you already have a mature workflow system.
| piskov wrote:
| Given Microsoft's track record, come back in a few years and see
| if it still lives.
|
| > It brings together and extends ideas from Semantic Kernel and
| AutoGen projects, combining their strengths while adding new
| capabilities
|
| ... and giving a hint what will happen to the aforementioned
| projects.
|
| --
|
| It's a shame when someone's promotion is tied to how many new
| things they ship.
|
| --
|
| > To learn more about migrating from either Semantic Kernel or
| AutoGen, see the Migration Guide from Semantic Kernel and
| Migration Guide from AutoGen.
|
| It seems the motto of Microsoft for the last 15 years: "You won't
| have time for new features -- all you'll do is migrations."
| nlawalker wrote:
| Fire and motion:
| https://www.joelonsoftware.com/2002/01/06/fire-and-motion/
| zkmon wrote:
| Why throw in .net in the mix? That alone could squish all
| interest.
| rubenvanwyk wrote:
| .Net is better fit for this than Python for sure?
| Izikiel43 wrote:
| What's the issue with net?
|
| It's a modern cross platform open source language with very
| good performance
| lomase wrote:
| .Net has never been something most of HN cares about.
| skydhash wrote:
| One of my grips with C#, Java,... is pushing runtime logic
| inside the type system. This leads to a huge standard library
| where there are multiple classes that are barely different
| than other other than implementation details.
|
| I prefer Go's approach on preferring interfaces instead of
| inheritance. But what I like is Clojure and Lisp where the
| semantics of algorithms and data structure is not so diffuse.
| dangoodmanUT wrote:
| > Semantic Kernel and AutoGen pioneered the concepts of AI agents
| and multi-agent orchestration
|
| Said nobody?
| bitwize wrote:
| I remember when "Microsoft Agent" meant the APIs that gave rise
| to Clippy, Rover, and (regrettably) even Bonzi Buddy.
|
| The bitter irony is, Microsoft has since embrace-extend-
| extinguished Bonzi Buddy spyware tech, building it right into
| Windows 11. So... they're moving onward to the future I guess?
| WarOnPrivacy wrote:
| > I remember when "Microsoft Agent" meant the APIs that gave
| rise to Clippy, Rover, and (regrettably) even Bonzi Buddy.
|
| I remember Microsoft Agents as the enforcement arm of the
| Business Software Association.
|
| They'd perform copyright raids on small biz, typically after
| some disgruntled employee phoned in an infringement tip.
| jeroenhd wrote:
| I've toyed with the idea of hooking up something like Copilot
| to Clippy to make an "agent" using the Microsoft Agents API.
|
| Unfortunately, the API died in Windows Vista, and was only
| widely available in Windows XP at the latest.
|
| API documentation seems rather sparse too, though it looks like
| an LLM somewhere found a pirated book or something with example
| code because generated code seems to understand the API and its
| restrictions decently well. Writing the kind of C++ that still
| compiles on old versions of Windows is what broke my will to
| finish the project, though.
| seba_dos1 wrote:
| I remember writing a Delphi application that spawned and used
| an agent, and even creating my own character when I was a
| teenager, so it surely wasn't _that_ sparse.
|
| Reimplementations exist too: https://mklab.eu.org/clippy/
| shireboy wrote:
| I have used this in a "beta" feature for an enterprise app and
| really like it. In ~100 lines of code I have a secured OpenAI
| compatible endpoint that I can chat with, and write tools for in
| .NET. I have it doing natural language query over some data and
| it works quite well.
|
| You can also expose the agents as MCP, AGUI and so it can be a
| tool you integrate with other AI platforms.
| tjpnz wrote:
| Haven't used Microsoft Agent in decades. Nice to hear they're
| reviving it.
| pamelafox wrote:
| I'm on the Python advocacy team at Microsoft, so I've been
| experimenting a bit with the new framework. It works pretty well,
| and is comparable to Langchainv1 and Pydantic-AI, but has tighter
| integrations with Microsoft-specific technologies. All the
| frameworks have very similar Agent() interfaces as well as graph-
| based approaches (Workflow, Langgraph, Graph).
|
| I have a repository here with similar examples across all those
| frameworks: https://github.com/Azure-Samples/python-ai-agent-
| frameworks-...
|
| I started comparing their features in more details in a gist, but
| it's WIP:
| https://gist.github.com/pamelafox/c6318cb5d367731ce7ec01340e...
|
| I can flesh that out if it's helpful. I find it fascinating to
| see where agent frameworks converge and diverge. Generally, the
| frameworks are converging, which is great for developers, since
| we can learn a concept in one framework and apply it to another,
| but there are definitely differences as you get into the edge
| cases and production-level sophistication.
___________________________________________________________________
(page generated 2025-12-24 23:01 UTC)