AI BriefingAWS Labs Releases 'CAO', a Multi-Agent Tool for Orchestrating Multiple AI Coding CLIs in Parallel
Key point
AWS Labs has open-sourced CAO, a multi-agent orchestrator that enables parallel or sequential control of various AI coding CLIs, including Claude Code and Codex.
Details
AWS Labs has released the CLI Agent Orchestrator (CAO). CAO runs multiple AI coding CLIs in isolated terminal sessions based on a local server, allowing a supervisor to delegate tasks to workers in parallel or sequentially.
Key Features and Supported Environments
CAO maintains each agent as an independent CLI process, leveraging native authentication and features as-is. The supported providers are as follows:
- Supported CLIs: Kiro CLI, Claude Code, Codex CLI, Antigravity CLI, Hermes, Kimi CLI, MiniMax Code, GitHub Copilot CLI, OpenCode CLI, Oh My Pi (OMP) CLI, Cursor CLI, Grok Build CLI
- Required Environment: Python 3.10+, tmux 3.3+, uv
Operation and Scalability
Users run cao-server and then start a supervisor using the cao launch command from the project directory. Agent status can be monitored and controlled via the Web UI or tmux. It also offers complex orchestration capabilities, including Kubernetes (Amazon EKS) deployment, workflow pipelines, cross-session memory, and self-learning loops.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Worktrunk CLI Released for Managing Git Worktrees for Parallel AI Coding AgentsOpen-Source Tool 'Evidence Graph' Released to Enforce 100% Skill Guideline Compliance in AI Code
Foremerge v0.5.0 Released: Rust-Based Open-Source Tool Detects Intent Conflicts Between Parallel AI Coding AgentsToken-Space Font Compiler Generates Fonts with Fixed Token Widths