Back to directory

agent-manager

A tmux-based terminal manager for running several AI coding agent CLIs, such as Claude Code, Codex, OpenCode, Grok Build and Gemini CLI, side by side, each in its own persistent session, with live status, prompt dispatch and diff review.

agent-manager

agent-manager is a layer over the coding-agent CLIs already installed on a machine: each session launches the real tool with its own login, subscription, configuration files and MCP servers, running in its own persistent tmux session. Every session appears in one foldable, reorderable project tree with live status, so it is not necessary to hunt through terminal tabs to see which agent is done or stuck.

A prompt can be sent into a session's pane without attaching to it, a dead session can be revived on its existing conversation, and a full-file diff of what an agent changed opens with syntax highlighting; comments left on lines are sent back to the agent as one review prompt. A session's conversation can also continue in a separate named fork. Mouse support covers scrolling, focusing, dragging sessions between groups and opening links.

A shell can be opened under a selected agent or group for builds, Git and other one-off commands. It is written in Go.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.