microsoft/project-oagents

Experimental AI Agents Framework

What it solves

This framework simplifies the creation and hosting of event-driven AI agents, providing a structured approach for developers to build complex agentic workflows within the .NET ecosystem.

How it works

It is an opinionated framework built on top of Semantic Kernel and Orleans, leveraging these technologies to enable agents to communicate and collaborate via events.

Who it’s for

.NET developers who want to build scalable, event-driven AI agent systems using Microsoft's AI and distributed systems tools.

Highlights

  • Built on Semantic Kernel and Orleans
  • Supports event-driven agent architectures
  • Includes examples for automating GitHub development teams, marketing campaigns, and support center orchestration

Related

  • Project
    microsoft/debug-gym

    A text-based interactive debugging framework for Python programs that allows LLM agents to use tools like pdb and bash to investigate and fix bugs in code repositories.

  • Project
    browser-use/browser-use-pi

    A TypeScript SDK that enables AI agents to control Chrome browsers by writing and executing JavaScript via a persistent V8 REPL and raw CDP.

  • Project
    praveen-ks-2001/hermes-agent-template

    A Railway deployment template for Hermes Agent that adds a web-based admin dashboard for easy configuration, gateway management, and user pairing.

  • Project
    straylabs-ai/deadend-cli

    An autonomous web application penetration testing agent that uses feedback-driven iteration and custom payload generation to find and exploit vulnerabilities.