# openai/codex-action

Repository: https://github.com/openai/codex-action
Canonical: https://ross.abutalabs.com/products/codex-action
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T00:12:45+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 24
- inputs: {"age_days": 336, "days_push": 8, "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 1209, forks 159 (observed 2026-08-28T04:03:59.784958+00:00)

## What it is
A GitHub Action that runs OpenAI's Codex CLI inside GitHub Actions workflows, installing the CLI and routing API calls through a secure proxy to the Responses API. It lets teams automate tasks like code review, PR commenting, and code generation with fine-grained permission profiles controlling filesystem and network access.

## Use cases
- run codex code review on every pull request
- build a pull request bot that posts AI review comments
- automate code fixes in CI with an AI agent
- run openai codex cli in github actions workflow
- restrict AI agent permissions in CI pipelines
- use azure openai models in github actions

## When to choose
- you want AI-powered code review or PR automation directly in GitHub Actions
- you need tight control over what an AI agent can access in CI
- you want to use your own OpenAI or Azure API key for workflow automation

## When to avoid
- you prefer Codex cloud's hosted code review without managing workflows
- your CI runs outside GitHub Actions
- you need a general-purpose agent framework rather than a GitHub Action

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, llm-inference, ci-cd, code-review, security
- domain: developer-tools, large-language-models, version-control
- platform: cloud, cli
- tags: github-actions, openai-codex, pull-request-automation, code-review-bot, typescript, automation, ai-agents, docker

## Member repositories
- openai/codex-action (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:59.784958+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 2026-08-30T06:18:36.143456+00:00, confidence not recorded.
  - readme: https://github.com/openai/codex-action (fetched 2026-08-28T04:03:59.784958+00:00, sha 9b5de8efb27e)
- Data as of 2026-08-30T08:39:29.467469+00:00.