# tom-doerr/zsh_codex

This is a ZSH plugin that enables you to use OpenAI's Codex AI in the command line.

Repository: https://github.com/tom-doerr/zsh_codex
Canonical: https://ross.abutalabs.com/products/zsh_codex
Language: Python
License: MIT
License Family: permissive
Topics: zsh, openai, codex, ai
Last push: 2025-03-22T23:56:40+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 12, release rhythm 35, longevity 100
- inputs: {"age_days": 1805, "days_push": 529, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1734, forks 96 (observed 2026-08-28T04:05:28.959875+00:00)

## What it is
A ZSH plugin that brings AI-powered code completion to the command line, supporting OpenAI Codex, Google Gemini, and other LLM providers. Users write a comment or variable name and the AI generates the corresponding shell command or code.

## Use cases
- generate shell commands from natural language comments
- get AI code completion in the zsh terminal
- use OpenAI Codex or Gemini from the command line
- autocomplete complex shell commands with AI
- write commands by describing them in plain English

## When to choose
- you use zsh and want AI-assisted command generation in your terminal
- you want a lightweight plugin that works with oh-my-zsh or plain zsh
- you want to switch between multiple LLM providers like OpenAI, Gemini, Groq, or AWS Bedrock

## When to avoid
- you use bash or fish instead of zsh
- you need a full GUI AI assistant rather than inline shell completion
- you cannot or will not provide API keys for a cloud LLM provider

## Facets
- artifact type: plugin
- maturity: active
- function: llm-inference, cli, developer-tools
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: cli, python
- tags: zsh, zsh-plugin, openai, codex, gemini, ai-completion, command-line-assistant, command-line, linux, macos

## Member repositories
- tom-doerr/zsh_codex (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:28.959875+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 2026-08-30T03:31:26.764815+00:00, confidence not recorded.
  - readme: https://github.com/tom-doerr/zsh_codex (fetched 2026-08-28T04:05:28.959875+00:00, sha 2224af3f8e8d)
- Data as of 2026-08-30T08:39:29.467469+00:00.