agent-deck
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
How to use
The agent-deck is a terminal session manager designed for AI coding agents, providing a unified text-based user interface (TUI) for interacting with various models such as Claude, Gemini, OpenCode, and Codex. Developers can streamline their coding workflow by easily switching between different AI tools without needing to leave the terminal, enhancing productivity and efficiency in coding tasks.
Once connected to the agent-deck server, you can interact with the available AI coding agents through simple command inputs. The TUI allows you to send queries or commands tailored for each specific tool, enabling you to generate code snippets, debug existing code, or receive explanations of code functionality. For optimal results, you can issue clear and concise prompts, ensuring the AI understands your intentions effectively.
How to install
To install agent-deck, you need to have Node.js installed on your machine.
Option A: For a quick start using npx (no global installation required), you can run:
npx -y agent-deck
Option B: If you prefer a global installation, you can use the following command:
npm install -g agent-deck
Make sure that you have the latest version of Node.js installed to avoid compatibility issues.
Additional notes
When setting up the agent-deck, ensure you configure any necessary environment variables that might be required for your specific AI tools to function correctly. A common pitfall is neglecting to set these variables, which can lead to unexpected errors. Additionally, familiarize yourself with the documentation of each AI model you intend to use to leverage their full capabilities effectively.
Related MCP Servers
superset
IDE for the AI Agents Era - Run an army of Claude Code, Codex, etc. on your machine
OpenContext
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
deepcontext
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agents for faster, smarter context on large codebases.
forge-orchestrator
Forge Orchestrator: Multi-AI task coordination. File locking, knowledge capture, drift detection. Rust.
sub-agents
Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.
langfuse
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability