Microsoft's conversational multi-agent framework where agents exchange messages to collaborate, critique, and complete tasks.
Five passes over the same idea, each from a different angle. Do them in order, or jump to whichever you need.
AutoGen treats multi-agent communication as a conversation protocol. Each agent has a name, system prompt, and capability set. Agents talk to each other (and optionally to humans) to solve problems collaboratively. AutoGen's human-proxy agent enables human-in-the-loop verification without changing the agent code. The async-first v0.4 rewrite significantly improved reliability for production workloads.
