microsoft/intelligent-terminal

A fork of Windows Terminal with native agent integration, right in your command line.

What it solves

It integrates AI agents directly into the terminal environment, eliminating the need to copy-paste shell output into a separate AI chat window for troubleshooting or command generation. It provides a native way to interact with AI assistants that have direct context of the active terminal session.

How it works

This is an experimental fork of Windows Terminal that acts as a local transport layer. It connects to any Agent Client Protocol (ACP)-compatible agent CLI (such as GitHub Copilot CLI) via stdio. The terminal captures shell output and prompts, passing them to the selected agent CLI, which then returns suggestions or commands. Users can run suggested commands with explicit approval.

Who it’s for

Developers and system administrators using Windows who want an AI-enhanced command-line experience with integrated context-aware assistance.

Highlights

  • Agent Pane: A docked, context-aware chat interface for interacting with agents across multiple shells (PowerShell, Bash/WSL).
  • Error Detection: Automatically detects command failures and provides a one-click option to send the error context to the agent for a fix.
  • BYOK (Bring Your Own Key): Supports custom providers and local models (e.g., via Ollama) using OpenAI-compatible Chat Completions endpoints.
  • Command Palette Integration: Allows users to trigger agent tasks directly from the command palette using a ? prefix.
  • Agent Management: A dedicated panel to track active agent sessions and resume previous workflows.

Related

  • Project
    aandrew-me/tgpt

    A cross-platform CLI tool that allows users to interact with AI models directly from their terminal.

  • Project
    MoonshotAI/kimi-cli

    A terminal-based AI agent that helps developers complete software development tasks and terminal operations by reading code, executing shell commands, and searching the web.

  • Project
    carlos-algms/agentic.nvim

    A Neovim chat interface for AI agents that implements the Agent Client Protocol (ACP), allowing users to use any ACP-compatible provider with their existing terminal configurations.

  • Project
    ConardLi/easy-agent

    Easy Agent is a terminal‑based AI coding assistant that can read, edit, and run code under configurable permission rules and optional OS sandboxing. It supports major LLM providers, offers persistent sessions, extensibility via plugins/skills, and multiple safety modes (plan, auto, default). Install via npm, trust a workspace, then interact with the REPL to ask questions, make multi‑file changes, run tests, and undo actions.

  • Project
    ZeroDayEvil/ai-security-tool

    AI Security Tool is an open‑source, cross‑platform suite that combines a multi‑protocol terminal (SSH, RDP, VNC, etc.) with AI‑driven security automation. It offers supply‑chain & CVE scanning, LLM‑based command assistance, and a set of 12+ autonomous agents that handle tool selection, recon, attack‑chain building, and fault tolerance. Available as native installers for Windows, macOS, Linux, Android, and as a web UI, it targets red‑teamers, bug‑bounty hunters, and CTF players looking for a unified AI‑native workflow.