Agent Deck

Agent Deck is an open-source terminal dashboard for running and monitoring multiple AI coding agents in parallel. It displays each session’s status, active tool, working directory, and last prompt in real time, with Vim-style keyboard navigation for creating, focusing, closing, and renaming panes. It supports Claude Code and OpenCode through automatically installed hooks and runs as the single-binary `dot-agent-deck`, with native embedded terminal panes and no external terminal multiplexer required. The dashboard runs inside terminals including Ghostty, iTerm2, Alacritty, Kitty, and WezTerm, while preserving the agent clients’ existing shortcuts, skills, and configurations. Per-project TOML configuration can pair an agent with side panes for test runs, log tails, or `kubectl` watches. macOS and Linux installation is available through Homebrew, Nix, prebuilt binaries, or source builds; Windows use is currently through WSL. The project is distributed under the MIT license.

TrueDeck is a terminal-first multi-agent coding workbench for running several coding agents on the same repository in separate live terminal panes. It supports agents including Grok, Codex, Cursor, Claude, and Gemini while retaining their native command-line interfaces rather than presenting them in a chat webview. It provides split panes, tabs, focus control, and workspace restoration, with repository-specific and global memory plus MCP and project-context synchronization handled in the background. Installers and portable builds are distributed through the project's GitHub Releases, and the repository is licensed under the MIT license.

Codeman is a self-hosted web dashboard for running and monitoring AI coding agents. It launches Claude Code, OpenCode, Codex, Antigravity, Gemini, Pi, or Grok in persistent tmux sessions, with an optional plain shell, and streams their terminals to a browser. Sessions persist across restarts and network drops; idle detection can re-prompt agents, resume them after usage limits reset, and run scheduled jobs, while live floating windows show background agents and subagents. The dashboard is designed for touch devices and includes local echo, QR login, swipe navigation, and push notifications. It can run locally, in Docker, or over SSH, is MIT licensed, runs on the user's machine by default, and states that it has no telemetry.

Multi-Agent Workbench is a local-first browser control room for orchestrating coding agents such as Claude Code, Codex CLI, and generic PTY-based command-line agents. Agents work in task rooms under editable YAML role cards that define permissions, speaking style, and decision boundaries; a rule-driven orchestrator pauses execution and risky commands for human approval, while persistent sessions expose terminal activity and status. The system uses a local event-driven architecture with a React interface, Fastify backend, REST API, server-sent events, agent adapters, an approval service, and a SQLite event store. Every action passes through the API and is recorded in an append-only event log, whose events are projected into timelines, decisions, terminal views, artifacts, and diff views. It also provides task templates, Markdown reports and decision logs, real-time room updates, and configurable risk resolutions. Code-writing agents are intended to use isolated Git worktrees, with diff and patch review before changes reach the main workspace; the repository marks this worktree and merge flow as in progress.

ManyAgents is a native macOS app for running teams of Claude Code and Codex coding agents in one window. Each project has an orchestrator that splits a request into tasks, opens agent tabs, and tracks their work. Workers build tasks in separate Git worktrees, thinkers handle difficult design or cross-codebase decisions, and read-only reviewers check completed work. It includes project and agent views, a built-in browser with signed-in browser takeover for testing web applications, an iOS Simulator panel for checking iPhone builds, and a needs-you view for agent questions and recommendations. It runs agents through the user's existing Claude Code and optional Codex accounts, keeping code on the Mac and stating that it has no analytics. Claude Code and macOS 14 or later are required; Claude Code requires a Claude subscription or Anthropic API key. The app offers a 14-day trial followed by a stated one-time license purchase.