Skip to content

tcapelle/termGPT

Repository files navigation

PyPI version

termGPT: Chatbot in the Terminal

TermGPT v1.0.0 introduces exciting new features including improved conversation history management and experimental function-calling support for executing Linux commands from your terminal. This program uses Gemini Flash by default, but any LiteLLM model is supported.

Now you can use the llm command (Like Simon's tool)

In this version, these have been consolidated into a single entry point:

$ llm "list all files in this folder with sizes"

If you want to chat with Claude, you can use the -m flag:

$ llm -m claude-3-5-sonnet-20240620

Install

You will need an GEMINI API key, which should be available as an environment variable named GEMINI_API_KEY.

$ pip install termgpt

Usage

Interactive Chat:

$ llm
> let's check git status
To check the git status, use the command `git status`. This command will show you the current status of your git repository, including any modified, staged, or untracked files.

Run Terminal Commands:

You can execute commands by passing them as a quoted argument:

$ llm "list all files in this folder with sizes"
Use `ls -l` to list all files in the current directory, along with their sizes, modification dates, and permissions.
Execute this command (press return to run): 
$ ls -l
-rw-r--r--  1 user staff   2.4K Mar 6 09:43 README.md
...

Happy chatting!

About

A simple wrapper to call openAI's chatGPT on the terminal written in Python

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages