AutoGen
Vannus records that this vendor routes across several model providers — not captured by one. Every finding below is quoted to the vendor’s own document, or marked not disclosed where the vendor publishes nothing.
Microsoft's open-source framework for building multi-agent LLM applications — agents converse to complete tasks, with support for tool use and human-in-the-loop steps.
In many cases, agents need access to LLM model services such as OpenAI, Azure OpenAI, or local models.
Microsoft states AutoGen receives no new features and is now community managed, and points new users to Microsoft Agent Framework instead. In the vendor’s own words: “AutoGen is now in maintenance mode.” github.com ↗
This is the vendor’s own announcement, not our forecast. It does not change the grade above, which measures the product as it stands — but it is the kind of fact a resilience score exists to surface, so it sits here rather than in a footnote.
Not yet assessed. We publish a sovereignty position only where the vendor documents one — we do not infer it from a domain or a company name.
Vannus publishes a nine-dimension trust framework — data sovereignty, training privacy, compliance posture, operational resilience, exit portability, and more. The heaviest criterion asks whether the tool builds its own AI or resells someone else's model; where the vendor discloses it, the grade cites the vendor's own documentation. No paid placements — scoring is walled off from affiliate revenue. See the methodology →