Skip to main content
llm.info
Back to Companies
Microsoft logo

Creator of the Phi model family and Copilot products.

4
Models
2
Apps
7
Tools

AutoGen

MAINTENANCE MODE. AutoGen is Microsoft's open-source framework for building multi-agent AI applications, where agents converse and collaborate to solve tasks. Supports tool use, human-in-the-loop, and a layered architecture (Core, AgentChat, Extensions). Microsoft has placed AutoGen in maintenance mode: its README states the project will receive no new features and is community managed, and directs new users to Microsoft Agent Framework. The repository is not archived.

Guidance

Guidance is Microsoft's library for controlling large language models with structured generation. It enables interleaving generation, prompting, and logical control into a single continuous flow, uses context-free grammar (CFG) to guarantee valid output formats like JSON, and achieves 50% faster inference through token healing and prompt caching. Supports all major LLM providers with a simple, intuitive syntax.

Microsoft Foundry

Microsoft Foundry "unifies agents, models, and tools under a single management grouping with built-in enterprise-readiness capabilities including tracing, monitoring, evaluations, and customizable enterprise setup configurations", managed as one Azure resource with unified RBAC, networking and policy. Microsoft documents access to "more than 10,000 models from Microsoft, OpenAI, Anthropic, Meta, and others", declarative prompt agents and container-based hosted agents, and developer surfaces spanning the Foundry portal, SDKs, the Azure Developer CLI, a VS Code extension and an MCP server. This is the vendor's current name: Microsoft's own "Evolution of Foundry" table records the brand moving from "Azure AI Studio / Azure AI Foundry" to "Microsoft Foundry", so do not file it under the old name. The GA line is narrower than the platform's marketing suggests: the portal is generally available for core scenarios only, while Monitoring, Memory, agent Guardrails, the Operate tab (Overview, Assets, Compliance) and Foundry's own AI Gateway all remain in preview, Workflows is preview and "Foundry is retiring workflows on December 1, 2026", and standalone Azure OpenAI resources and hub-based projects are not supported in the new portal at all.

Microsoft MCP Servers

Microsoft's catalog of official Model Context Protocol server implementations, giving agents structured access to Microsoft services. It spans the Azure MCP Server, GitHub integration, Azure DevOps tooling and Microsoft 365 data access, providing first-party servers for enterprises that would otherwise rely on community implementations of the same integrations.

ONNX Runtime

ONNX Runtime is Microsoft's cross-platform engine for high-performance inference and training of ONNX models, with hardware acceleration across CPU, GPU, and NPUs and a dedicated generative-AI path for LLMs.

Playwright MCP

Microsoft's Model Context Protocol server that gives AI agents structured, accessibility-tree-based control of a browser via Playwright - navigating pages, clicking, and extracting content without screenshots or pixel guessing.

Semantic Kernel

Semantic Kernel is Microsoft's open-source SDK for integrating LLMs into applications. It supports C#, Python, and Java with features like planners, plugins, and memory management.