Tier 4 · Open-source coding agents Coding agents · fetched 2026-07-02

AutoGen

Microsoft's multi-agent framework built on conversational agents: agents (and humans) converse to solve tasks, with group chats, tool use, and code execution woven into the conversation model.

View source on GitHub

Key takeaways

01
Conversation as the coordination substrate between agents
02
Human-in-the-loop is a first-class participant, not an afterthought

Flows built on this research

Agent Architecture

Single-Agent vs Multi-Agent: Decide and Design

A decision flow for the most expensive architecture choice in agent systems - grounded in what actually ships versus what demos well.

4 steps · 45-75 minutes