Intelligent Terminal
Intelligent Terminal adds native agent integration to Windows Terminal for ACP-compatible CLI help on supported Windows 11.
What is Intelligent Terminal?
Intelligent Terminal is an experimental fork of Windows Terminal that adds native agent integration directly into the command line. It keeps the terminal features users expect from Windows Terminal, including tabs, profiles, themes, settings, shells, and keyboard shortcuts, while adding an agent pane and related controls for working with an ACP-compatible agent CLI.
The project is designed for Windows 11 22H2 or later and requires a supported agent CLI and subscription. GitHub Copilot is the default agent option, but the terminal can also work with other ACP-compatible agent CLIs, including Copilot, Claude, Codex, Gemini, and custom or local agents when configured.
Key Features
- Native agent integration in the terminal, so users can ask questions and get help without leaving their shell workflow.
- Agent pane that can be toggled, focused, and opened with error context for working alongside command output.
- Agent management and prompt-mode command palette for switching agents and issuing agent-related commands.
- Automatic detection of ACP-compatible agent CLIs on the machine, with GitHub Copilot CLI used as the default when no supported agent is found.
- Error detection and error suggestions that can send detected command failures to the agent for possible fixes.
- Configurable agent settings such as agent choice, model, pane placement, and shell-integration behavior.
How to Use Intelligent Terminal
Install Intelligent Terminal from the Microsoft Store or with WinGet, then launch it on a supported Windows 11 system. On first run, choose or sign in to an agent, and let the app detect any compatible agent CLI already installed.
After setup, use the terminal as usual and open the agent pane when you want help interpreting output, troubleshooting an error, or asking a question about your current shell session. Most agent-related shortcuts and behaviors can be customized in settings.
Use Cases
- Troubleshooting a failed command by opening the agent pane with the error context already attached.
- Getting help from an agent while staying in the same terminal session, without copying and pasting output into a separate chat app.
- Switching between different agent CLIs or models from the agent management controls when a different workflow is needed.
- Using a prompt-mode command palette to send agent commands or open agent-related views quickly from the keyboard.
- Running the terminal with a preferred local or custom ACP-compatible agent after configuring it in settings.
FAQ
- Does Intelligent Terminal replace Windows Terminal features? No. The project keeps core Windows Terminal capabilities such as tabs, profiles, themes, settings, shells, and keyboard shortcuts.
- What agents does it work with? It works with ACP-compatible agent CLIs. The documentation mentions GitHub Copilot as the default and also refers to Copilot, Claude, Codex, and Gemini detection.
- What platform is required? The README says it requires Windows 11 22H2 or later (22621.6060+).
- Can it help with command failures? Yes. It includes error detection and can pass detected errors to the agent for suggested fixes.
- Do I need to install an agent separately? Not necessarily. If no supported agent CLI is found, the app defaults to GitHub Copilot CLI and installs it via WinGet.
Alternatives
- Windows Terminal: the upstream terminal app without the native agent integration layer described here.
- A standard command-line tool plus a separate AI chat app: keeps terminal and AI assistance in separate windows instead of combining them in one workflow.
- Other terminal emulators with customization features: useful if you want a different terminal environment, but they may not offer ACP-based agent integration.
- Standalone agent CLI tools: better if you want an agent in the shell without replacing your terminal application.
Alternatives
AakarDev AI
AakarDev AI is a powerful platform that simplifies the development of AI applications with seamless vector database integration, enabling rapid deployment and scalability.
Arduino VENTUNO Q
Arduino VENTUNO Q is an edge AI computer for robotics, combining AI inference hardware and a microcontroller for deterministic control. Arduino App Lab-ready.
Devin
Devin is an AI coding agent that helps software teams complete code migrations and large refactoring by running subtasks in parallel.
Biji
Biji is a versatile platform designed to enhance productivity through innovative tools and features.
Codex Plugins
Use Codex Plugins to bundle skills, app integrations, and MCP servers into reusable workflows—extending Codex access to tools like Gmail, Drive, and Slack.
Ably Chat
Ably Chat is a chat API and SDKs for building custom realtime chat apps, with reactions, presence, and message edit/delete.