agentskillexchange Manage multi-agent coding sessions from one terminal mission control with Agent Deck
Use Agent Deck when an operator needs one keyboard-first terminal to monitor, switch, fork, sandbox, and organize many coding-agent sessions instead of juggling tabs, panes, and worktrees by hand.
Prerequisites
Agent Deck, tmux-compatible terminal, one or more supported coding agents such as Claude Code, Codex, Gemini CLI, or OpenCode
Installation
Use the upstream install or setup path that matches your environment:
- brew install asheshgoplani/tap/agent-deck
- go install github.com/asheshgoplani/agent-deck/cmd/agent-deck@latest
- git clone https://github.com/asheshgoplani/agent-deck.git && cd agent-deck && make install
- Homebrew install: run brew upgrade asheshgoplani/tap/agent-deck.
Requirements and caveats from upstream:
- New worktree location depends on the layout:
Docker Sandbox
- Run sessions inside isolated Docker containers. The project directory is bind-mounted read-write, so agents work on your code while the rest of the system stays protected.
Basic usage or getting-started notes:
Features . Conductor . Install . Quick Start . Docs . Discord . FAQ
Five minutes from zero to a Telegram bot that watches every Claude session you have running.
bash
Extracted from upstream docs: https://raw.githubusercontent.com/asheshgoplani/agent-deck/HEAD/README.md