amux vs AutoGen (Microsoft)

AutoGen is a framework for building multi-agent systems. amux is an orchestrator for running Claude Code agents. Different levels of abstraction.

AutoGen is Microsoft's open-source framework for building multi-agent conversation systems — you program agent interactions in Python. amux is an operational tool for running Claude Code (AI coding agents) in parallel with a web dashboard, shared board, and self-healing infrastructure.

Key differences

FeatureamuxAutoGen
PurposeOperational agent fleet managementAgent interaction framework
Agent typeClaude Code (coding-specialized)General-purpose LLM agents
SetupClone + run, web dashboard in minutesRequires Python programming
Web UIFull dashboard with peek, board, mobileNo built-in UI
Self-healingBuilt-in watchdog for coding agentsCustom implementation needed
Task coordinationSQLite kanban with atomic claimingCustom implementation needed
User typeDevelopers using Claude CodeDevelopers building agent systems

Different Levels of Abstraction

AutoGen is a framework — you use it to build custom multi-agent systems. amux is an operator — you use it to run Claude Code agents doing real coding work. They operate at different levels of abstraction.

When to use AutoGen

When you're building a custom multi-agent application — research tools, complex reasoning systems, automated workflows that require programming custom agent interactions. AutoGen gives you the primitives to build whatever you need.

When to use amux

When you want to run Claude Code agents to actually write code in your repositories — right now, with a UI, self-healing, and a task board. amux is operational where AutoGen is foundational.

Get started with amux

Run dozens of Claude Code agents in parallel. Python 3 + tmux. Open source.

git clone https://github.com/mixpeek/amux && cd amux && ./install.sh
amux register myproject --dir ~/Dev/myproject --yolo
amux start myproject
amux serve  # → https://localhost:8822
View on GitHub