🐢 Lazy Terminal

🐢 Lazy Terminal

By Heterohabilis GitHub

An LLM-based smart terminal for lazy guys :P

react python
Overview

What is Lazy Terminal?

Lazy Terminal is an intelligent command-line assistant that connects language models with external tools through MCP (Modular Component Protocol), enabling seamless terminal automation and smart interaction.

How to use Lazy Terminal?

To use Lazy Terminal, install the required packages with pip install -r requirements.txt, configure your model credentials in config/models.yaml, and launch the assistant with python main.py.

Key features of Lazy Terminal?

  • Dynamic Tool Routing: Automatically chooses between direct response or tool invocation.
  • Contextual Memory: Maintains conversation context for up to 50 interactions.
  • Multi-model Support: Easily integrate various language models via Coagent.
  • Robust JSON Handling: Extracts and processes structured model responses.
  • Secure Bash Execution: Runs safe, controlled bash scripts through MCP tools.

Use cases of Lazy Terminal?

  1. Automating file management tasks in the terminal.
  2. Executing complex commands with minimal user input.
  3. Integrating various AI models for enhanced command-line interactions.

FAQ from Lazy Terminal?

  • Can Lazy Terminal execute any bash command?

Yes, it can execute safe and controlled bash commands through its MCP tools.

  • Is Lazy Terminal easy to set up?

Yes, with a simple installation and configuration process, you can get started quickly.

  • What programming languages does Lazy Terminal support?

Lazy Terminal is primarily built with Python and supports various language models.

Content

🐢 Lazy Terminal

Lazy Terminal is an intelligent command-line assistant that connects language models with external tools through MCP (Modular Component Protocol). It dynamically determines whether a query should be directly answered or passed to a registered tool, enabling seamless terminal automation and smart interaction (you are lazy; it isn't).


🔧 Features

  • Dynamic Tool Routing: Automatically chooses between direct response or tool invocation.
  • Contextual Memory: Maintains conversation context (default 50 interactions).
  • Multi-model Support: Easily integrate various language models via Coagent.
  • Robust JSON Handling: Extracts and processes structured model responses.
  • Secure Bash Execution: Runs safe, controlled bash scripts through MCP tools.

🚀 Quick Start

Installation

pip install -r requirements.txt

Configuration

  • Edit config/models.yaml to include your model credentials.
  • Edit config/mcp_servers.yaml to list your MCP servers.

Running

Launch the assistant with:

python main.py

Start interacting with Lazy Terminal directly from your console!


🛠 Example Usage

Start the bash runner server:

python test_servers/bash_runner.py

Sample interaction:

User input:

You: List all .txt files in ~/Documents and save output to files.txt

Assistant tool invocation:

{
  "tool_name": "run_bash_script",
  "parameters": {
    "commands": "ls ~/Documents/*.txt > files.txt"
  }
}

Lazy Terminal will then execute this safely and return the results.


🔑 Environment Variables

Set model API keys as environment variables, e.g.:

export DEEPSEEK_API_KEY="your-api-key"

Ensure they match your settings in models.yaml.


📌 Roadmap

  • Implement advanced memory compression.
  • Add interactive UI (terminal/web).
  • Enhance error handling and logging.
  • Extend toolset (e.g., file handling, browser automation).
  • Multi-tool calling

🤝 Credits

Enjoy building your intelligent terminal assistant!

No tools information available.
MCP Server
MCP Server by Cavumnigrum

Test MCP server that can do several things

mcp-server python
View Details
mcp-server-test
mcp-server-test by taemyung-heo

-

mcp-server-test python
View Details

-

mcp-server python
View Details

A python-based MCP server for google calendar

google-calendar python
View Details
StickyNotes-MCP
StickyNotes-MCP by pranav-js670

A Python MCP server for Sticky Notes that demonstrates how to create custom tools, resources, and prompts using the Model Context Protocol (MCP) to integrate seamlessly with the Claude Desktop App.

mcp python
View Details

A Serverless MCP implementation using SST, React and AWS.

react aws
View Details