Centrally manage AI agents
Create, pair, control, monitor: Agent Manager gives you full management over your AI agents — per project and across all projects.
cockpit
control
Management instead of uncontrolled growth
Anyone using multiple agents needs control: Who exists, what are their permissions, what are they currently doing? Agent Manager makes this visible and controllable.
What you control
Authorization mode, model and provider per agent, coupling with the terminal, history — and at project level roles, rules and knowledge.
This will help you specifically
Create & link
Create agents and make them ready for use.
Permissions
Read/plan, write, full access per agent.
Status & Live
See who is working or waiting.
Course
Conversation history per agent.
Custom agents
Manage your own roles.
Export/Import
Save configuration.
Become a tester for Agent Manager
Early access, direct line to the creators, influence on the roadmap. We are looking for agencies, freelancers, and teams working with Claude Code and/or OpenAI Codex on Mac.
Pre-register for the beta nowmacOS · active Claude and/or OpenAI subscription · no costs, no payment details.