terminator 🤖 Mediar.ai

https://github.com/user-attachments/assets/00329105-8875-48cb-8970-a62a85a9ebd0

🚀 What's new

• 08/25 Big release — NodeJS SDK in YAML workflows, run JS in browser, OS event recording → YAML generation in MCP, and more
• 08/25 we raised $2.8m to give AI hands to every desktop ⚠

AI-powered desktop automation — open source, MIT-licensed, cross-platform, accessibility-first. Works across all apps and browsers. Inspired by GitHub Actions & Playwright. 100x faster than generic AI agents, >95% success rate, no vendor lock-in.

🧠 Why Terminator

For Developers

• Create automations that work across any desktop app or browser
• Runs 100x faster than ChatGPT Agents, Claude, Perplexity Comet, BrowserBase, BrowserUse
• >95% success rate without costly consultant armies (UIPath, Automation Anywhere)
• MIT-licensed — fork it, ship it, no lock-in

We achieve this by pre-training workflows as deterministic code, and calling AI only when recovery is needed.

For Teams

Our private beta workflow builder + managed hosting = plug-and-play automation engine for your business:

• Record & map your processes in days
• Deploy AI to execute them at >95% accuracy
• Kill repetitive work without legacy RPA complexity or cost

⚡ Quick start: MCP

Install the Terminator MCP in Claude Code with one command:

claude mcp add terminator "npx -y terminator-mcp-agent@latest" -s user

Or install via the MCP directory for other clients.

⚡ Quick start: CLI

macOS/Linux

curl -fsSL https://mediar.ai/install.sh | bash

Windows

In powershell:

irm https://mediar.ai/install.ps1 | iex

After Installation

Run the setup command to configure your environment:

terminator setup

This will:

• ✅ Install the Chrome extension automatically (please do not use keyboard/mouse for a few seconds)
• ✅ Check system requirements (VC++ redistributables on Windows)
• ✅ Configure SDKs and dependencies
• ✅ Verify the MCP agent is ready

⚡ Quick start: programmatic control

🐍 Python

import terminator

# Control applications programmatically
desktop = terminator.Desktop()
desktop.open_application('calc')
desktop.locator('name:Seven').click()
desktop.locator('name:Plus').click()
desktop.locator('name:Three').click()
desktop.locator('name:Equals').click()
# Result: 10 appears in calculator

Installation:

pip install terminator

🟦 TypeScript / Node.js

const { Desktop } = require("terminator.js");

// Async/await for modern control flow
const desktop = new Desktop();
await desktop.openApplication("notepad");
await desktop.locator("name:Edit").typeText("Hello from TypeScript!");
await desktop.pressKey("{Ctrl}s"); // Save

Installation:

npm install terminator.js
# or: bun add terminator.js

Feature Support

While Terminator aims for full cross-platform support, current capabilities vary by OS. Windows is the primary development target and has the most complete feature set.

Legend:

• ✅: Supported - The feature is stable and well-tested.
• 🟡: Partial / Experimental - The feature is in development and may have limitations.
• ❌: Not Supported - The feature is not yet available on this platform.

🕵️ How to Inspect Accessibility Elements (like name:Seven)

To create reliable selectors (e.g. name:Seven, role:Button, window:Calculator), you need to inspect the Accessibility Tree of your OS. Here's how to explore UI elements on each platform:

🪟 Windows

• Tool: Accessibility Insights for Windows
• Alt: Inspect.exe (comes with Windows SDK)
• Usage: Open the app you want to inspect → launch Accessibility Insights → hover or use keyboard navigation to explore the UI tree (Name, Role, ControlType, AutomationId).

These tools show you the Name, Role, ControlType, and other metadata used in Terminator selectors.

🍎 macOS

• Tool: Accessibility Inspector
• Usage: Comes with Xcode → Open Xcode > Open Developer Tool > Accessibility Inspector → Use the target icon to explore UI elements on screen.

🐧 Linux

• Tool: Accerciser

• Install:

  sudo apt install accerciser
  

• Usage: Launch Accerciser → Select the window/app → Browse the accessible widget tree.

💡 Tip

Once you identify the structure of your UI:

# Sample pattern
desktop.locator('window:Calculator')
       .locator('role:Button')
       .locator('name:Seven')

You can build and debug selector paths incrementally using .locator() chaining.

Explore Further

• Examples

Troubleshooting

For detailed troubleshooting, debugging, and MCP server logs, see the MCP Agent documentation.

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests. many parts are experimental, and help is appreciated. join our Discord to discuss.

Businesses

If you want desktop automation at scale for your business, let's talk.

Investors

louis@mediar.ai