Get multi-terminal functionality for AI coding agents. For founders using Claude, Codex, Gemini CLI.
intermediateโฑ 30 minutes๐ต Free + open-source
227 stars40 forksTypeScriptQuality 8/10Updated 7/6/2026100% free ยท open source
What it is
Use wmux to launch multiple AI tools at once in separate windows on your Windows computer.
What you can make with it
Automations like: use Claude Code to generate text, open the result in Gemni CLI, and then automate browser interactions with MCP.
How it helps
wmux saves time by allowing you to use multiple AI tools in parallel without needing to switch between them.
Real use case example
"A founder wants to write a blog post with Claude Code and then share it on social media with Gemini CLI. They launch both tools in separate windows with wmux and complete their tasks efficiently."
If you're new
New users should pick up wmux when they need to use multiple AI tools at once but don't know how to configure tmux.
If you're senior
Senior engineers and developers can use wmux to optimize their workflows and reduce the number of windows open.
Common confusion cleared up
wmux is not a replacement for tmux, it's an alternative designed specifically for AI agents and automation tasks.
Best inside these AI tools
Claude DesktopClaude CodeCodex CLI
Pairs with
Claude APIGemini CLIMCP browser automationCodex CLI
Why we list it on WorkflowStacks: wmux is included as a free and open-source alternative to tmux that works well with AI tools like Claude.
What it does
wmux provides multi-terminal functionality for AI coding agents, allowing founders to split terminals for Claude, Codex, and Gemini CLI with MCP browser automation on Windows without requiring WSL
Install / run
git clone https://github.com/openwong2kim/wmux.git && cd wmux
When to use it
โขYou need to run multiple AI coding agents simultaneously on a Windows machine
โขYou want to automate browser interactions with your AI agents using MCP
โขYou prefer a native Windows alternative to tmux for managing multiple terminals
Quick start
1Run `npm install` to set up the project
2Configure your AI agents in the `config.json` file, specifying the terminals and agents to use
3Start wmux with `npm start` to launch the multi-terminal interface
4Use the `split` command to divide the terminal into multiple panes for each AI agent
5Use the `select` command to focus on a specific pane and interact with the corresponding AI agent
Ready-to-paste prompt
split claude codex gemini-cli --mcp-url https://example.com --config config.json
Heads up: Make sure you have Node.js and npm installed on your Windows machine, as wmux is built using TypeScript and relies on these tools to run
Saves to your device
Topics
agentic-ai
ai-agent
ai-agents
ai-coding
browser-automation
claude
claude-code
coding-agent
developer-tools
electron
gemini
mcp-server
multi-agent
powershell
terminal-multiplexer
tmux
tmux-alternative
windows
What's inside โ free to inspect
No purchase needed
Read the entire source before you build โ unlike paid marketplaces that hide it behind a buy button.