Introducing the Codex app (https://openai.com/index/introducing-the-codex-app/)

OpenAI just released a new macOS app for their Codex coding agent. I’ve had a few days of preview access - it’s a solid app that provides a nice UI over the capabilities of the Codex CLI agent and adds some interesting new features, most notably first-class support for Skills (https://developers.openai.com/codex/skills), and Automations (https://developers.openai.com/codex/app/automations) for running scheduled tasks.

The app is built with Electron and Node.js. Automations track their state in a SQLite database - here’s what that looks like if you explore it with uvx datasette ~/.codex/sqlite/codex-dev.db:

Here’s an interactive copy of that database in Datasette Lite (https://lite.datasette.io/?url=https%3A%2F%2Fgist.githubusercontent.com%2Fsimonw%2F274c4ecfaf959890011810e6881864fe%2Fraw%2F51fdf25c9426b76e9693ccc0d9254f64ceeef819%2Fcodex-dev.db#/codex-dev).

The announcement gives us a hint at some usage numbers for Codex overall - the holiday spike is notable:

Since the launch of GPT‑5.2-Codex in mid-December, overall Codex usage has doubled, and in the past month, more than a million developers have used Codex.

Automations are currently restricted in that they can only run when your laptop is powered on. OpenAI promise that cloud-based automations are coming soon, which will resolve this limitation.

They chose Electron so they could target other operating systems in the future, with Windows “coming very soon (https://news.ycombinator.com/item?id=46859054#46859673)”. OpenAI’s Alexander Embiricos noted on the Hacker News thread (https://news.ycombinator.com/item?id=46859054#46859693) that:

it’s taking us some time to get really solid sandboxing working on Windows, where there are fewer OS-level primitives for it.

Like Claude Code, Codex is really a general agent harness disguised as a tool for programmers. OpenAI acknowledge that here:

Codex is built on a simple premise: everything is controlled by code. The better an agent is at reasoning about and producing code, the more capable it becomes across all forms of technical and knowledge work. […] We’ve focused on making Codex the best coding agent, which has also laid the foundation for it to become a strong agent for a broad range of knowledge work tasks that extend beyond writing code.

Claude Code had to rebrand to Cowork (https://simonwillison.net/2026/Jan/12/claude-cowork/) to better cover the general knowledge work case. OpenAI can probably get away with keeping the Codex name for both.

OpenAI have made Codex available to free and Go (https://simonwillison.net/2026/Jan/16/chatgpt-ads/) plans for “a limited time” (update: Sam Altman says two months (https://x.com/sama/status/2018437537103269909)) during which they are also doubling the rate limits for paying users.

Tags: sandboxing (https://simonwillison.net/tags/sandboxing), sqlite (https://simonwillison.net/tags/sqlite), ai (https://simonwillison.net/tags/ai), datasette (https://simonwillison.net/tags/datasette), electron (https://simonwillison.net/tags/electron), openai (https://simonwillison.net/tags/openai), generative-ai (https://simonwillison.net/tags/generative-ai), llms (https://simonwillison.net/tags/llms), ai-agents (https://simonwillison.net/tags/ai-agents), coding-agents (https://simonwillison.net/tags/coding-agents), codex-cli (https://simonwillison.net/tags/codex-cli)