# TheR1D/shell_gpt

A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.

Repository: https://github.com/TheR1D/shell_gpt
Canonical: https://ross.abutalabs.com/products/shell_gpt
Language: Python
License: MIT
License Family: permissive
Topics: cheat-sheet, cli, gpt-3, openai, productivity, shell, chatgpt, python, terminal, linux, commands, gpt-4, llm, llama, ollama, gpt-5
Last push: 2026-07-02T06:03:01+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 51, longevity 94
- inputs: {"age_days": 1323, "days_push": 62, "days_rel": 119, "gap_med": 196.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12259, forks 979 (observed 2026-08-28T04:10:52.169968+00:00)

## What it is
ShellGPT (sgpt) is a Python command-line productivity tool that uses LLMs like GPT-4/5 or local models via Ollama to generate shell commands, code snippets, documentation, and answers directly in the terminal. It supports stdin piping and redirection, making it easy to analyze logs, generate commit messages, and get quick answers without leaving the shell.

## Use cases
- generate shell commands from natural language descriptions
- analyze docker or app logs and find errors with suggested fixes
- generate git commit messages from a diff
- summarize documents from the terminal
- get quick answers to technical questions without a browser
- use local LLMs with Ollama for free offline queries

## When to choose
- you want an AI assistant embedded in your terminal workflow
- you frequently forget shell command syntax and want instant generation
- you pipe logs, diffs, or files into an LLM for analysis
- you want a lightweight pip-installable CLI that works across shells and OSes

## When to avoid
- you need a polished chat UI or conversation history management
- you require optimized performance with local open-source models
- you don't want to pay for an OpenAI API key and can't self-host a backend
- you need structured agent workflows or tool calling rather than single prompts

## Facets
- artifact type: cli-tool
- maturity: active
- function: llm-inference, cli, chatbot, developer-tools
- domain: developer-tools, large-language-models
- platform: cli, windows, python, cross-platform
- tags: shell-commands, openai, ollama, gpt, terminal-assistant, stdin-piping, command-line, linux, macos

## Member repositories
- TheR1D/shell_gpt (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:52.169968+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:14:13.344066+00:00, confidence not recorded.
  - readme: https://github.com/TheR1D/shell_gpt (fetched 2026-08-28T04:10:52.169968+00:00, sha a712e34647dc)
  - registry_pypi: https://pypi.org/pypi/shell_gpt/json (fetched 2026-08-29T08:11:34.708766+00:00, sha 21a4a71f041f)
- Data as of 2026-08-30T08:39:29.467469+00:00.