agent-manager is an open-source developer tool created by Yoan Wainmann designed to optimize command-line workflows when coding alongside multiple AI agents. Distributed as a lightweight, single Go binary under the Apache-2.0 license, it consolidates popular AI CLI agents—including Claude Code, Codex, OpenCode, Gemini CLI, Grok, and Pi—into a single live-status tmux environment.

Built specifically for power users and terminal-centric developers, agent-manager streamlines multitasking across multiple AI assistants with dedicated keyboard shortcuts and deep tool integration:

Quick Responses: Tap the space bar to respond to blocked AI agents instantly without manually attaching to their session.
Conversation Forking: Press f to fork an active conversation thread into a named sibling session to explore alternative coding paths.
Integrated Terminal: Press T to pin a standard terminal shell alongside your active AI agents for manual execution.
Structured Diff Reviews: Use ctrl+r to review whole-file diffs and add line comments, which aggregate into a single structured prompt sent back to the agent.
Git Worktree Isolation: Launch agent sessions directly inside isolated Git worktrees to keep experimental AI code modifications neatly organized.
Session Persistence: Operating on standard tmux sessions, your background agent tasks continue running unhindered even if you exit the manager UI.

agent-manager runs natively on macOS and Linux platforms, and supports Windows via WSL2.

Pros of agent-manager

Unified tmux view for tracking Claude Code, Codex, OpenCode, Gemini CLI, Grok, and Pi sessions with live statuses
Productivity-focused hotkeys for quick responses (`space`), thread forking (`f`), and pinned terminal shells (`T`)
Built-in diff viewer (`ctrl+r`) that aggregates line comments into a single AI review prompt
Ability to spawn AI sessions into isolated Git worktrees to safeguard main project branches
Distributed as a single Go binary under an open-source Apache-2.0 license

Cons of agent-manager

Terminal-based tmux interface presents a learning curve for developers accustomed to GUI IDEs
Windows compatibility requires operating through WSL2 rather than a native Windows Command Prompt or PowerShell

Frequently Asked Questions

Which AI agents does agent-manager support?

agent-manager natively aggregates Claude Code, Codex, OpenCode, Gemini CLI, Grok, and Pi within a consolidated tmux environment complete with live status tracking.

What platforms are compatible with agent-manager?

agent-manager is distributed as a single Go binary that runs natively on macOS and Linux, as well as Windows environments operating through WSL2.

How does agent-manager handle code diffs and reviews?

Pressing `ctrl+r` opens whole-file diffs where developers can leave line comments. These inline notes are automatically aggregated into a single, structured review prompt sent directly back to the active AI agent.

Will my tmux sessions close if I quit agent-manager?

No, standard tmux sessions remain active in the background even after you exit the agent-manager user interface, allowing long-running tasks to continue uninterrupted.