asheshgoplani/agent-deck

Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

What it solves

Agent Deck acts as a centralized command center for managing multiple AI coding agents simultaneously. It solves the problem of "agent sprawl," where developers running several instances of tools like Claude Code or OpenCode across different projects struggle to track their status, manage costs, or switch between sessions efficiently.

How it works

It provides a terminal-based interface (TUI) that registers and monitors all your active AI agent sessions. It allows you to group sessions, fork them to explore different coding approaches without losing context, and attach specific tools or skills to individual agents. It also includes a "Conductor" feature that can orchestrate a fleet of agents, allowing you to supervise them via mobile messaging apps like Telegram or Slack.

Who it’s for

This tool is designed for power users and developers who rely heavily on AI coding agents and need a structured way to manage, monitor, and scale their AI-assisted workflows across multiple repositories.

Highlights

  • Unified TUI: Manage all agent sessions, view status, and switch between them with single keystrokes.
  • Fleet Orchestration: Use the Conductor to supervise multiple agents and receive updates on your phone.
  • Flexible Configuration: Supports per-group Claude account overrides, environment variables, and declarative group settings.
  • Session Management: Easily fork sessions to test new ideas, attach MCP servers, and manage skills without manual config file editing.
  • Cross-Platform: Works on macOS, Linux, and Windows (via WSL).

Related

  • Project
    T1mn/pad

    A tmux-native TUI workspace for managing multiple terminal AI agents, allowing users to preview conversation history and jump between sessions quickly.

  • Project
    graykode/abtop

    A TUI monitoring dashboard for AI coding agents that tracks token usage, context windows, and rate limits across multiple active sessions.

  • Project
    ajsahni/agents-office

    Agents Office is a beta, locally‑run visual platform that turns Claude into a team of 35 role‑based AI agents. You type tasks, the system routes them to the right agent (or a team), the agents use Claude Code connectors (Gmail, Slack, Chrome, etc.) to do the work, and results are saved as notes in your personal “Brain”. Features include customizable briefs/skills, recurring routines, a calendar view, team‑splitting, model/effort selection, and a non‑commercial license.

  • Project
    jamesrochabrun/AgentHub

    A macOS desktop hub for managing multiple AI coding agent sessions (Claude Code and Codex) with integrated terminal, GitHub support, and live previews.

  • Dispatch
    OtoDock 1.6.0 – Self‑hosted AI Agent Platform for Company‑wide Automation

    OtoDock 1.6.0 is a self‑hosted, multi‑tenant platform that lets companies create, share and run Claude Code or Codex agents across departments, with built‑in security, scheduling, phone integration and a rich UI.