← Discover MCPs and Agents
t
MCPAI & MLGitHub

tAI

tAI is an AI terminal assistant CLI that helps you with Linux and macOS commands.

Links

Repository

README

From the repo.

tAI, a terminal AI assistant

tAI is a CLI that helps you with Linux and macOS terminal commands. Just ask it a question, and it will use AI to suggest a command and explain what it does. If you like the suggestion, the script can automatically run the command for you in your terminal.

Demo

Why & What?

  • Github Copilot CLI syntax feels clunky to me
  • Faster than using Gemini, ChatGPT or similar in a browser
  • Simpler to find answers without checking man pages
  • NEW: Support for multiple AI providers (OpenAI, Google, Anthropic, Groq)
  • NEW: Interactive TUI setup using inquirer for provider and model selection
  • NEW: Enhanced terminal UI with rich for better readability and prompts
  • NEW: Now you can run commands right from this command-line interface

However, never trust the output entirely.

Installation

# install pipx (if you don't have it)
brew install pipx
pipx ensurepath

# install TAI
pipx install terminal-ai-assistant

Usage

On your first run, tai will guide you through a quick, interactive setup process to choose your AI provider, select a model from a curated list, and enter your API key. This information will be securely stored in ~/.config/tai/config.json.

Once configured, you can use tai with your queries:

$ tai kill port 3000

# Example output (formatted with rich):
╭────────────────────────────────────────────────── Command ───────────────────────────────────────────────────╮
│ kill $(lsof -t -i :3000)                                                                                     │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

Execute the command: kill $(lsof -t -i :3000)? [y/n]:

Development

pip install --user pipenv
pipenv --python 3.11
pipenv install

pipenv run tai kill port 3000

Collected info

  • ★ 96 stars
  • ⎇ 10 forks
  • Language: Python
  • Source updated: 6/30/2026

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.