🔥 openai/codex
Lightweight coding agent that runs in your terminal — Trending on GitHub today with 2390 new stars.
npm i -g @openai/codexor brew install --cask codex
Codex CLI is a coding agent from OpenAI that runs locally on your computer.
If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.
If you want the desktop app experience, run codex app or visit the Codex App page.
If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.
Quickstart
Installing and running Codex CLI
Install globally with your preferred package manager:
# Install using npm npm install -g @openai/codex# Install using npm npm install -g @openai/codex# Install using Homebrew brew install --cask codex# Install using Homebrew brew install --cask codexThen simply run codex to get started.
You can also go to the latest GitHub Release and download the appropriate binary for your platform.
Each GitHub Release contains many executables, but in practice, you likely want one of these:
- macOS
Apple Silicon/arm64: codex-aarch64-apple-darwin.tar.gz x86_64 (older Mac hardware): codex-x86_64-apple-darwin.tar.gz
- Linux
x86_64: codex-x86_64-unknown-linux-musl.tar.gz arm64: codex-aarch64-unknown-linux-musl.tar.gz
Each 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.
Using Codex with your ChatGPT plan
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.
Docs
-
Codex Documentation
-
Contributing
-
Installing & building
-
Open source fund
This repository is licensed under the Apache-2.0 License.
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
githubtrendingopen-source![[P] PhAIL (phail.ai) – an open benchmark for robot AI on real hardware. Best model: 5% of human throughput, needs help every 4 minutes.](https://d2xsxph8kpxj0f.cloudfront.net/310419663032563854/konzwo8nGf8Z4uZsMefwMr/default-img-graph-nodes-a2pnJLpyKmDnxKWLd5BEAb.webp)
[P] PhAIL (phail.ai) – an open benchmark for robot AI on real hardware. Best model: 5% of human throughput, needs help every 4 minutes.
I spent the last year trying to answer a simple question: how good are VLA models on real commercial tasks? Not demos, not simulation, not success rates on 10 tries. Actual production metrics on real hardware. I couldn't find honest numbers anywhere, so I built a benchmark. Setup: DROID platform, bin-to-bin order picking – one of the most common warehouse and industrial operations. Four models fine-tuned on the same real-robot dataset, evaluated blind (the operator doesn't know which model is running). We measure Units Per Hour (UPH) and Mean Time Between Failures (MTBF) – the metrics operations people actually use. Results (full data with video and telemetry for every run at phail.ai ): Model UPH MTBF OpenPI (pi0.5) 65 4.0 min GR00T 60 3.5 min ACT 44 2.8 min SmolVLA 18 1.2 min Teleop / Fi
Convert PDF to HTML5: Preserving Layout
Whether you are a developer building a web application or a company aiming to digitize a massive archive, you have likely struggled to find the ideal way to display your files. You might transform a stylishly designed document to HTML, only to discover fonts are missing, images have shifted, and tables are a disorganized mess. If maintaining visual accuracy is your main goal, one particular solution outperforms all the others: BuildVu. Below is why BuildVu remains the top professional option for turning PDFs into HTML while keeping your original document design perfectly intact. The Challenge: Why Most Solutions Fail Most PDF-to-HTML software isn't optimized for high-quality transformation. These tools try to estimate where paragraphs conclude and where columns start. Since PDF uses a lock
LangExtract: Streamlined Information Extraction with Gemini
Executive Summary LangExtract, developed by Google, is a Python library designed for efficient information extraction from unstructured text. With its integration of Gemini-powered models, it provides precise source grounding and structured data extraction. This article explores the mechanics of LangExtract, its real-world applications, and its potential to transform data processing workflows. Why LangExtract Matters Now The need for effective information extraction solutions has never been more pressing. With data generation reaching staggering levels—over 2.5 quintillion bytes daily—organizations are inundated with unstructured data. Traditional methods of data processing often fall short, leading to inefficiencies and errors. This is where LangExtract shines. By harnessing advanced LLM
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!