# openai/codex

Lightweight coding agent that runs in your terminal

Repository: https://github.com/openai/codex
Canonical: https://ross.abutalabs.com/products/codex
Language: Rust
License: Apache-2.0
License Family: permissive
Last push: 2026-08-27T00:42:45+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 36
- inputs: {"age_days": 507, "days_push": 7, "days_rel": 7, "gap_med": 1.5, "n_releases_24m": 149}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 118785, forks 18120 (observed 2026-08-28T04:12:24.124461+00:00)

## What it is
OpenAI's Codex CLI is a lightweight coding agent that runs locally in your terminal, helping you write, review, and refactor code with AI assistance. It is written in Rust, supports sign-in with a ChatGPT plan or API key, and also offers IDE and desktop app integrations.

## Use cases
- run an AI coding agent in my terminal
- refactor code from the command line with AI
- generate code fixes without leaving the shell
- use my ChatGPT plan for local coding assistance
- automate repetitive coding tasks in the terminal
- review and edit code with an LLM agent

## When to choose
- you want an AI coding assistant directly in your terminal
- you already have a ChatGPT Plus/Pro/Business plan
- you prefer a fast native Rust CLI over editor plugins
- you want local agent execution with optional API key auth

## When to avoid
- you need a fully offline coding assistant with no LLM backend
- you want a GUI-first experience rather than a terminal tool
- you require fine-grained control over model providers beyond OpenAI

## Facets
- artifact type: cli-tool
- maturity: active
- function: agent-framework, llm-inference, cli, developer-tools
- domain: developer-tools, artificial-intelligence
- platform: windows, cli, rust
- tags: coding-agent, terminal, openai, chatgpt, ai-pair-programming, command-line, ai-agents, macos, linux

## Member repositories
- openai/codex (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:24.124461+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 2026-08-29T16:11:38.921323+00:00, confidence not recorded.
  - readme: https://github.com/openai/codex (fetched 2026-08-28T04:12:24.124461+00:00, sha 5d3dbff15c4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.