← Discover MCPs and Agents
a
MCPAI & MLGitHub

ai-terminal

Your AI mate into your favourite terminal

Links

Repository

README

From the repo.

AI Terminal

A Tauri + Angular terminal application with integrated AI capabilities. AI Terminal Demo

Features

  • Natural language command interpretation
  • Integrated AI assistant
  • Command history and auto-completion
  • Cross-platform support (macOS, Windows, Linux)
  • Modern UI built with Tauri and Angular

Requirements

  • Node.js 18+
  • Rust and Cargo
  • For AI features: Ollama (can be installed with brew install ollama)

Development Setup

  1. Clone the repository:

    git clone https://github.com/your-username/ai-terminal.git
cd ai-terminal

  2. Install dependencies and run the project:

    cd ai-terminal
npm install
npm run tauri dev

Installation

macOS (Homebrew)

You can install AI Terminal using Homebrew:

brew tap AiTerminalFoundation/ai-terminal
brew install --cask ai-terminal

After installation, you can launch the application from Spotlight or run it from the terminal:

ai-terminal

Quick Guide to Using Ollama to Download macsdeve/BetterBash3 Model

Linux

  1. Install Ollama

Open your terminal and run:

curl -fsSL https://ollama.com/install.sh | sh
  1. Download the Model

Run the following command:

ollama pull macsdeve/BetterBash3

macOS

  1. Download Ollama
  1. Install Ollama
  • Open the downloaded .zip file from your Downloads folder.
  • Drag the Ollama.app into your Applications folder.
  • Open Ollama.app and follow any prompts.
  1. Download the Model

Open Terminal and execute:

ollama pull macsdeve/BetterBash3

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License

Collected info

  • ★ 150 stars
  • ⎇ 14 forks
  • Language: Rust
  • Source updated: 9/5/2026

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.