# dot-agent-deck

> dot-agent-deck is a dashboard for running several AI coding agents in parallel, in a terminal UI (the `dot-agent-deck` binary) or a desktop app. A background daemon owns the agents, so both clients show and control the same ones.

The pages below are the user documentation for the latest release, as Markdown. Links between pages are relative `.md` links and resolve against the linking page's URL.

If dot-agent-deck is already installed and its binary has the `docs` subcommand, prefer it: it prints these pages as they are for the installed version, with no network access. `dot-agent-deck docs` lists the topics, `dot-agent-deck docs <topic>` prints one page, and `dot-agent-deck docs --all` prints every page. A topic is the page's path below `/docs/` without `.md`, for example `dot-agent-deck docs desktop/voice`. Older releases do not have it: if `dot-agent-deck docs` reports an unrecognized subcommand, use these pages, which follow the latest release rather than the installed one.

Every page in one file: [llms-full.txt](https://agent-deck.devopstoolkit.ai/llms-full.txt)

## Start here, by goal

Getting Started ends with one running agent. When the user wants more than that, read the page for their goal as well:

- Install, upgrade or uninstall dot-agent-deck: read [Installation](https://agent-deck.devopstoolkit.ai/docs/installation.md)
- Start a first agent and check that the deck shows it: read [Getting Started](https://agent-deck.devopstoolkit.ai/docs/getting-started.md)
- Several agents working together, for example a coder, a reviewer and an orchestrator that hands them work: read [Orchestration](https://agent-deck.devopstoolkit.ai/docs/orchestration.md)
- Isolated background work, each task in its own copy of the repository: read [Dispatcher Mode](https://agent-deck.devopstoolkit.ai/docs/dispatcher-mode.md)
- Run a prompt on a schedule, or put agents on open GitHub issues: read [Schedules](https://agent-deck.devopstoolkit.ai/docs/scheduled-tasks.md)
- Run the agents on another machine over ssh: read [Remote Environments](https://agent-deck.devopstoolkit.ai/docs/remote-environments.md)
- Use the desktop app: read [Desktop App](https://agent-deck.devopstoolkit.ai/docs/desktop/index.md)
- Settings and environment variables: read [Configuration](https://agent-deck.devopstoolkit.ai/docs/configuration.md)
- Something is not working: read [Troubleshooting](https://agent-deck.devopstoolkit.ai/docs/troubleshooting.md)

## Docs

- [Getting Started](https://agent-deck.devopstoolkit.ai/docs/getting-started.md): Install the binary, launch the deck, start one agent and check each step, then find the next feature to set up.
- [Installation](https://agent-deck.devopstoolkit.ai/docs/installation.md): Install, verify, upgrade and uninstall the dot-agent-deck binary (Homebrew, release download, Nix or source), its agent hooks, and the desktop app; inspect and stop the local daemon.
- [Session Management](https://agent-deck.devopstoolkit.ai/docs/session-management.md): What each agent status and card marker means in both clients, and how to detach from, resume or clear your workspace.
- [Orchestration](https://agent-deck.devopstoolkit.ai/docs/orchestration.md): Set up a multi-role orchestration in .dot-agent-deck.toml, start it in either client, and the full role, delegate and work-done reference.
- [Idle Workers & Notifications](https://agent-deck.devopstoolkit.ai/docs/idle-workers-and-notifications.md): What the deck reports to an orchestrator about a stuck, waiting, blocked or exited worker, and how to tune or turn the reports off.
- [Dispatcher Mode](https://agent-deck.devopstoolkit.ai/docs/dispatcher-mode.md): Start background work units (one agent or a team) from a dispatcher pane, check they started, and clean up afterwards.
- [Schedules](https://agent-deck.devopstoolkit.ai/docs/scheduled-tasks.md): Run a prompt on a cron schedule, or dispatch agents onto open GitHub issues: set up, check, troubleshoot, plus the full schedules.toml, cron and schedule CLI reference.
- [Configuration](https://agent-deck.devopstoolkit.ai/docs/configuration.md): Every configuration file and environment variable: config.toml (default_command, default_dir, bell), the project .dot-agent-deck.toml, the experimental flag, and the desktop app's desktop.toml.
- [Remote Environments](https://agent-deck.devopstoolkit.ai/docs/remote-environments.md): Run the deck and its agents on a remote host over ssh: connecting, detaching, reattaching, version skew and failure modes.
- [Remote Environment Requirements](https://agent-deck.devopstoolkit.ai/docs/remote-requirements.md): What a Linux or macOS host must provide before dot-agent-deck remote add can register it as a remote.
- [Remote Recipes](https://agent-deck.devopstoolkit.ai/docs/remote-recipes.md): Bootstrap commands for a Linux or macOS host, the reverse-tunnel recipes, and reading remote doctor's output.
- [Keyboard Shortcuts](https://agent-deck.devopstoolkit.ai/docs/keyboard-shortcuts.md): Every TUI keyboard shortcut and mouse action, and how to customize them in keybindings.toml.
- [Desktop App](https://agent-deck.devopstoolkit.ai/docs/desktop/index.md): What the desktop app (alpha) is, what it needs to run, and what it has and lacks compared with the TUI.
- [Dashboard](https://agent-deck.devopstoolkit.ai/docs/desktop/dashboard.md): The desktop app's main screen: agents per daemon, their statuses, the agent pane, and closing agents and orchestrations.
- [New Agent](https://agent-deck.devopstoolkit.ai/docs/desktop/new-agent.md): Start an agent from the desktop app: choose the daemon, the directory, the mode and the command.
- [Daemons](https://agent-deck.devopstoolkit.ai/docs/desktop/daemons.md): Watch local and remote (ssh) daemons from the desktop app: add, test, choose and remove them; the list is shared with the CLI's remotes.toml.
- [Settings](https://agent-deck.devopstoolkit.ai/docs/desktop/settings.md): The desktop app's settings and desktop.toml: appearance, zoom, the settings file's keys, and the app's keyboard shortcuts.
- [Voice Control](https://agent-deck.devopstoolkit.ai/docs/desktop/voice.md): Turn on and use voice control in the desktop app: dictating to an agent in typing mode, choosing between matches, the speech and command services it needs, their settings, and what is sent where.
- [Troubleshooting](https://agent-deck.devopstoolkit.ai/docs/troubleshooting.md): Symptoms, causes and fixes for common problems with logs, hooks, spawning agents, upgrades, delegation, panes, configuration, schedules, remotes and the desktop app.
- [License](https://agent-deck.devopstoolkit.ai/docs/license.md): The license dot-agent-deck is distributed under (MIT).