Maestro – Run AI coding agents autonomously for days (Free/OSS) (github.com)

Maestro, a new cross-platform desktop application, has been launched to automate the orchestration of AI coding agents, allowing users to run these agents autonomously for extended periods—up to 24 hours continuously. Designed specifically for developers who handle multiple projects simultaneously, Maestro enables collaborative creation of detailed specification documents, which can then be executed automatically. This significantly reduces manual tasks, enhances productivity, and allows developers to maintain clean contexts for each task, avoiding context bleed. The tool supports various AI agents, including Claude Code, OpenAI Codex, and OpenCode, with plans to integrate more based on community needs. Key features include a command-line interface for automation, a mobile remote control for monitoring agents, customizable workflows through playbooks, and robust session history management. Maestro's emphasis on a specification-first approach encourages a more structured coding process, fostering iterative refinement and clearer documentation of development tasks—transforming how developers interact with AI in software development.