aiagentrank.io
Codex CLI logo

Codex CLIv0.6

OpenAI’s open-source terminal agent for refactors, audits and migrations.

B70💻CodeSemi-autonomousOpen sourceOpen source
49k
openai.com

Agent Rank breakdown

Agent Rank
70/ 100
BB-tier
Autonomy
8
Capabilities
4
Integrations
4
Pricing
10
Polish
6
Verifiability
10

Auto-computed from autonomy, capabilities, integrations, pricing, maturity and editorial verification. Updated every deploy. How is this computed?

Capabilities

  • Code
  • Tool use

Integrations

Version control
GitHub
Terminal / shell
Shell

Pricing tiers

Open source
Free
CLI-native engineers
  • +Apache-2.0 binary
  • +BYO OpenAI / Anthropic key
  • +Composable from Makefiles + scripts
Want the real monthly cost at your volume? Use the TCO calculator →Full Codex CLI pricing breakdown →

Pros & cons

Pros
  • +Zero-install terminal workflow — agent where engineers already live
  • +Open source under permissive license; auditable end-to-end
  • +Ideal for one-shot refactors, audits, and migrations
Cons
  • No long-running session UI; not built for hour-long autonomous work
  • Less polished than IDE-native alternatives
  • You wire the model key + handle rate limits
Ready to try Codex CLI?

OpenAI’s open-source terminal agent for refactors, audits and migrations. Start with the open source tier.

Install Codex CLI

Frequently asked questions

What is Codex CLI?+

Codex CLI is OpenAI's open-source terminal coding agent. Apache 2.0 license, BYO model API key (typically GPT-5 or any OpenAI-compatible endpoint). Sits in your shell and edits files, runs tests, opens PRs — same shape as Claude Code but OpenAI-built and fully open source.

Codex CLI vs Claude Code?+

Claude Code is bundled with Claude Pro ($20/mo includes tokens) and has the more polished autonomy loop. Codex CLI is open source (Apache 2.0) and uses your own API key — better for OpenAI-stack teams, audit-sensitive industries, or anyone who wants to fork the agent itself.

Does Codex CLI work with local LLMs?+

Yes — Codex CLI works with any OpenAI-compatible endpoint. Point it at Ollama, vLLM, or LM Studio and you can run it fully air-gapped with self-hosted models. This is one of its biggest advantages over Claude Code, whose local-LLM support is more limited.

User reviews

Write a review →
No reviews yet
50
40
30
20
10

Be the first to review. We verify every reviewer by email.

Your review of Codex CLI
Tap a star to rate

We'll send a one-time confirmation link to your email. Your address is hashed before storage — we never display it or share it. Reviews are moderated before going public.

Codex CLI is great for

Alternatives to Codex CLI

See all →
Codex CLI review 2026: pricing, features & alternatives · AI Agent Rank