Microsoft Foundry Agent Service
Microsoft Foundry Agent Service is a secure, enterprise-ready platform for designing, deploying, and orchestrating AI agents at scale. It gives teams a streamlined interface and toolset to automate complex workflows using multi-agent systems. Developers can build with hosted agents, custom code, or agent frameworks while taking advantage of Azure’s reliability, scalability, and integrated observability. Built-in tools, enterprise connectors, and Model Context Protocol support make it easy for agents to interact with business systems and organizational data. Security, access governance, and compliance are embedded throughout, allowing companies to maintain full control while deploying intelligent automation across critical processes. With one-click deployment to Microsoft 365 experiences, Foundry Agent Service accelerates how organizations operationalize AI in everyday work.
Learn more
AG2
AG2 is the open source AgentOS for building production-ready AI agents and multi-agent systems in minutes, not months. Formerly AutoGen, it provides an open source Python framework for building, orchestrating, and scaling AI agents that can collaborate through shared context, use tools, execute workflows, and support both autonomous and human-in-the-loop patterns. AG2 is designed for developers who want to build systems, not prompts, with simple and intuitive syntax, built-in conversation patterns, and a flexible platform for multi-agent automation. Agents in AG2 can extend their capabilities with tools, allowing them to interact with external systems, fetch real-time data, execute code, search the web, process documents, and complete complex tasks beyond a model’s internal knowledge. It supports many LLM providers and local models, including OpenAI-compatible endpoints, Anthropic Claude, Gemini through Vertex AI, DeepSeek, and LM Studio.
Learn more
Katara
Katara is a cutting-edge agentic workflow automation platform - manage a fleet of AI workers and extend your teams bandwidth.
From a single interface, manage technical Q&A across all community / social platforms like Discord, Telegram, with GitHub Discussions and Slack coming soon. Our agents can be configured to answer complex queries about your project directly or deliver responses into Private Team channels for human-in-the-loop review & editing - as your team answers, the model improves - making improvements to your content over time.
Create and deploy a custom agent in minutes on all supported platforms. Set your answer confidence threshold, we only respond directly if we exceed it. Manage your Q&A workflow from a single unified interface.
Learn more
Asteroid AI
Asteroid is an AI-driven browser-automation platform that lets both non-technical users and engineers build, deploy, monitor, and refine complex web workflows without writing traditional code. Its core is a graph-based agent builder where you describe desired tasks in natural language and configure repeatable logic with variables and structured outputs. Behind the scenes, Asteroid combines encrypted credential management, selector-based guardrails powered by Playwright, and live browser control to navigate pages, interact with UI elements, and call external APIs as needed. You can instantly deploy agents via a RESTful API, embed them into existing systems, or iterate in the platform’s console with real-time supervision, debugging tools, and human-in-the-loop checkpoints. Use cases range from multi-step data retrieval (insurance quotes, grant applications) and intelligent data entry into legacy systems (patient records, supplier portals) to automated reporting.
Learn more
