tmux-mcp
★ 57
vs
codex-agent
★ 13
tmux-mcp vs codex-agent
tmux-mcp: tmux-mcp-rs is a Rust-based Model Context Protocol (MCP) server that enables AI agents to programmatically interact with and manage tmux sessions. It allows agents to create, split, and run commands within tmux panes while providing structured output and real-time user observation, making terminal automation more reliable and efficient.; codex-agent: Codex Agent allows OpenClaw, an AI agent runtime, to autonomously operate the Codex CLI for programming tasks. It automates the entire coding workflow, from prompt generation and command approval to quality checks, freeing users from direct terminal interaction.
01
TL;DR
tmux-mcpWorkflow Automation · ★ 57
Automating Interactive Terminals: AI agents can create, manage, and operate within their own tmux sessions, allowing users to observe or participate in real-time.
codex-agentWorkflow Automation · ★ 13
Automating routine coding tasks, bug fixes, or minor feature additions without constant supervision.
02
Side-by-Side Comparison
Field
tmux-mcpcodex-agentCategory
Workflow Automation
Workflow Automation
Stars
★ 57
★ 13
License
MIT
—
Install Command
cargo install tmux-mcp-rs
git clone https://github.com/cyborgsalamanca/codex-agent.git ~/.openclaw/workspace/skills/codex-agent
Updated
3mo ago
4mo ago
Open Source
Yes
Yes
Tags
tmux, AI Agent, Workflow Automation
AI Agent, Code Automation, Terminal Automation
03
Features
tmux-mcp01AI Agent Control: Allows AI assistants to create, manage, and interact with tmux sessions, windows, and panes.
02Structured Interaction: Provides structured inputs and outputs for tmux commands, reducing ambiguity for agents compared to plain-text skills.
03Command Execution & Tracking: Enables execution of commands within panes and tracking their results, including exit codes and attributable output.
04Pane Content Capture & Search: Can capture pane content and offers advanced buffer search capabilities for large contexts.
05Remote & Isolated Operation: Supports controlling tmux sessions over SSH and using isolated sockets for agent-specific environments.
codex-agent01OpenClaw operates Codex via tmux sessions, mimicking human terminal interaction for persistent and observable execution.
02Automatic notification and OpenClaw awakening via hooks for task completion and approval requests, enabling hands-off operation.
03Intelligent prompt engineering and tool selection by OpenClaw, leveraging a comprehensive knowledge base before delegating tasks to Codex.
04Users can attach to the tmux session anytime to observe Codex's real-time output or take over the operation directly.
05Supports different approval modes (Codex auto or OpenClaw approval) configurable by the user based on task sensitivity.
04
Use Cases
tmux-mcp↳Automating Interactive Terminals: AI agents can create, manage, and operate within their own tmux sessions, allowing users to observe or participate in real-time.
↳Reliable Shell Automation for AI: Agents can execute complex shell commands and workflows, benefiting from structured outputs and stable IDs for sessions/windows/panes.
↳Incremental Context Exploration: Using buffer search tools, agents can explore large text contexts (like logs or codebases) incrementally without loading everything into LLM context.
↳Agent Orchestration and Parallel Execution: Running parallel commands across multiple windows/panes with monitoring for complex tasks.
↳Hardened Agent Sandboxing: Enforcing security policies, command filtering, and restricting agent access to specific sockets, sessions, or panes.
codex-agent↳Automating routine coding tasks, bug fixes, or minor feature additions without constant supervision.
↳Developing new features or refactoring code by simply stating high-level requirements in natural language to OpenClaw.
↳Enabling 'hands-off' development where OpenClaw manages the entire interaction with Codex and provides real-time updates via Telegram.
↳Iterative code improvement, where OpenClaw can automatically refine or retry tasks if initial results are unsatisfactory.
FAQ
FAQ
What is the difference between tmux-mcp and codex-agent?
Both tmux-mcp and codex-agent are in the Workflow Automation category. tmux-mcp has 57 stars, while codex-agent has 13 stars.
Which is better, tmux-mcp or codex-agent?
The best choice depends on your use case. Choose tmux-mcp if Automating Interactive Terminals: AI agents can create, manage, and operate within their own tmux sessions, allowing users to observe or participate in real-time., and codex-agent if Automating routine coding tasks, bug fixes, or minor feature additions without constant supervision..
Is tmux-mcp free or open source?
Yes, tmux-mcp is open source on GitHub (MIT).
Is codex-agent free or open source?
Yes, codex-agent is open source on GitHub.
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→