Google has open-sourced Scion, an experimental multi-agent orchestration testbed designed to manage concurrent agents in containers across local and remote compute environments. Scion functions as a "hypervisor for agents," integrating components such as agent memory, chatrooms, and task management while orchestrating "deep agents" like Claude Code and Gemini CLI.

Claude and Codex can collaborate as pair programmers, with one acting as the main worker and the other as a reviewer. Cursor researchers developed a multi-agent workflow where an orchestrator assigns tasks to various coding agents, mimicking human collaboration.

Cord coordinates multiple AI agents to handle complex tasks with dependencies and parallelism. LangGraph models task coordination as a state machine, allowing developers to define nodes and edges in Python for agent collaboration.