py-aiterm 0.0.1

A modern, voice-enabled AI terminal assistant with local LLM integration and Model Context Protocol (MCP) support.

ai_term is an open-source, voice-enabled terminal assistant that integrates LLMs (Large Language Models), Speech-to-Text (STT), and Text-to-Speech (TTS) into a powerful Command Line Interface (CLI) experience.

Features

• 🗣️ Voice Interaction: Talk to your terminal and hear responses back.
• 🧠 LLM Integration: Support for Local (Ollama) and Cloud (OpenAI, Anthropic) models.
• 🔌 MCP Support: Model Context Protocol client for extensible tool use.
• 🖥️ TUI Interface: Beautiful, responsive terminal UI built with Textual.
• ⚙️ Dynamic Configuration: Easy-to-use settings screen for managing providers and secrets.

Prerequisites

• Python 3.10+
• uv (recommended) or pip
• ffmpeg (required for audio processing)

Installation

From PyPI (Recommended for users)

pip install py-aiterm

From Source (For development)

1. Clone the repository:

   git clone https://github.com/vsaravind01/ai-term.git
   cd ai-term
   

2. Install dependencies:

   uv sync
   # OR with pip
   pip install -e .
   

Quick Start

The application runs as a distributed system with a main CLI and two support microservices.

1. Start Support Services

Run the following command to start the STT and TTS services in the background:

ai-term start

This pulls pre-built Docker images from GHCR and starts the services.

2. Check Status (Optional)

You can verify the services are running with:

ai-term status

3. Start the CLI

In your main terminal:

uv run ai-term

Documentation

Full documentation is available in the docs/ directory. To view it locally:

uv run mkdocs serve

• Setup Guide
• Docker Guide
• CLI Documentation
• API Reference

License

MIT