OpenAI's open-source coding agent built in Rust. Terminal-Bench 77.3% (GPT-5.3-Codex), SWE-bench Pro standardized 41.04%. 3-4x more token-efficient than Claude Code, 60-75% cheaper per task. Free with ChatGPT subscription, sandbox-first execution, 619 releases in 10 months.
85/100
Trust
66K+ ↑8%
Stars
7
Evidence
345.7 MB
Repo size
Product screenshot
Videos
Reviews, tutorials, and comparisons from the community.
OpenAI Codex CLI
Getting started with Codex
Using OpenAI Codex CLI with GPT-5-Codex
Repo health
13h ago
Last push
2,105
Open issues
8,844
Forks
383
Contributors
Editorial verdict
#2 coding CLI. Terminal-Bench 77.3% (GPT-5.3-Codex) and 3-4x more token-efficient. Sandbox-first safety is a genuine differentiator. Free with ChatGPT removes the cost barrier. Trails Claude Code by ~5pp on SWE-bench Pro standardized (41.04% vs 45.89%).
Source
GitHub: openai/codex
Docs: developers.openai.com
Public evidence
Codex surpassed 1.6M weekly active users (tripled since GPT-5.3 launch). Enterprise adopters include Cisco, Nvidia, Ramp, Rakuten.
90%+ of Codex code generated by Codex itself. Engineers run 4-8 parallel agents. Written in Rust for performance. 1M+ weekly devs, usage up 5x since Jan 2026.
Massive launch discussion. Top comments noted Claude Code outperformed early Codex on docs tasks. Shows improvement trajectory since launch.
Codex CLI leads Terminal-Bench 2.0 (62.9% vs Claude Code's 58.0%). Uses 3x fewer tokens. But Claude leads on OSWorld-Verified for GUI/computer-use tasks. Note: the 77.3% figure belongs to the Droid scaffold, not Codex CLI directly.
Ongoing independent coverage: tested porting JustHTML with Codex CLI, documented skills adoption, GPT-5 model improvements.
Codex CLI scores 77.3% with GPT-5.3-Codex on Terminal-Bench 2.0 — strong but no longer #1. ForgeCode (running Opus 4.6) leads at 81.8%. Codex CLI remains the strongest consumer CLI on terminal-native tasks.
Codex CLI scores 41.04% on SWE-bench Pro standardized, trailing Claude Code's 45.89% by ~5pp. The 56.8% score uses custom scaffolding and is not comparable to standardized results.
How does this compare?
See side-by-side metrics against other skills in the same category.
Growth
GitHub stars over time.
GitHub Stars
Where it wins
Terminal-Bench 77.3% (GPT-5.3-Codex) — strongest on terminal-native tasks (ForgeCode leads at 81.8%)
3-4x more token-efficient than Claude Code (Morph study), API pricing 60-75% cheaper ($1.50 vs $5.00 input)
Sandbox-first execution — genuine safety differentiator (caught SSRF that Claude Code missed per Blake Crosley)
Free with ChatGPT subscription — lowest barrier to entry
619 releases in 10 months — fastest iteration in the category
Native macOS + Windows app (Feb-Mar 2026) for parallel agent management
Where to be skeptical
SWE-bench Pro standardized: 41.04% trails Claude Code's 45.89% by ~5pp
Users report 20+ minute task times where Claude completes in <1 minute (HN: 104 pts thread). 'Too slow' is the consistent UX complaint
Tied to OpenAI models only
Ranking in categories
Featured in bundles
Know a better alternative?
Submit evidence and we'll run the full pipeline.
Similar skills
Aider
91Open-source AI pair programming CLI. The only tool in the coding CLI category with a fully verifiable, independent download number: 191,828/week PyPI installs, 5.7M lifetime, 15B tokens/week (homepage stat). Multi-model, git-native, no vendor lock-in. v0.86.2 released 2026-02-12.
Claude Code
90Anthropic's official agentic coding CLI. Terminal-native, tool-use-driven, with deep file system and shell access. #1 SWE-bench Pro standardized (45.89%), ~4% of GitHub public commits (SemiAnalysis), $2.5B annualized revenue (fastest enterprise SaaS to $1B ARR). 8M+ npm weekly downloads. Opus 4.6 with 1M context.
Gemini CLI
86Google's open-source terminal agent with Gemini 3 models, 1M token context, built-in Google Search grounding, and the best free tier in the category (1K req/day). 97.9K stars, 444 contributors. SWE-bench Pro standardized 43.30% (#2 behind Claude Code).
OpenCode
83Open-source AI coding agent from SST. v1.2.27 active (2026-03-16) — development resumed after a gap. OpenAI official partnership following the Anthropic OAuth block controversy. 124,766 GitHub stars (largest AI coding repo by star count). Known unauthenticated RCE fixed in v1.1.10+ (CVE, 432 HN pts).
Raw GitHub source
Constrained peek so you can sanity-check the source material without leaving the site.
Install globally with your preferred package manager:
# Install using npm
npm install -g @openai/codex
# Install using Homebrew
brew install --cask codex
Then simply run codex to get started.
Each GitHub Release contains many executables, but in practice, you likely want one of these:
codex-aarch64-apple-darwin.tar.gzcodex-x86_64-apple-darwin.tar.gzcodex-x86_64-unknown-linux-musl.tar.gzcodex-aarch64-unknown-linux-musl.tar.gzEach archive contains a single entry with the platform baked into the name (e.g., codex-x86_64-unknown-linux-musl), so you likely want to rename it to codex after extracting it.
Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Team, Edu, or Enterprise plan. Learn more about what's included in your ChatGPT plan.
You can also use Codex with an API key, but this requires additional setup.
This repository is licensed under the Apache-2.0 License.