Codex Chrome Extension + Codex App: A Working Guide for the May 2026 Launch
TL;DR
On May 7, 2026, OpenAI shipped the Codex Chrome extension. The interesting bit is not that Codex can now open a browser. It is that the browser already has all of your logins. Headless agents have been able to click around the web for two years. What changed is the agent now drives your actual Chrome profile, so it can update Salesforce, search Gmail, or scrape an internal Grafana dashboard without you handing over credentials. Permissions are per-site confirmation by default, the rollout has been bumpy in the first week, and EU/UK are excluded for now.
The Codex Chrome extension is not a new browser agent. It is the old browser agent that finally has your session cookie.
If you already use Codex CLI day-to-day, the Codex CLI real-world workflow covers the terminal side. This piece is about the Chrome bridge: what it does, what it does not, and where it fits in a 2026 coding setup.
What actually launched on May 7
OpenAI released two related things in the first half of May. The Chrome extension landed on May 7, 2026, alongside the Codex desktop app’s Plugins system. The official Codex changelog describes it like this:
“With the new extension for Chrome, Codex is even better at working with apps and websites in your browser. It works in parallel across tabs in the background without taking over your browser, and you stay in control of which websites Codex can use.”
A week later, on May 14, OpenAI added remote connections — the ability to use Codex from the ChatGPT mobile app by tethering to a Mac running the Codex desktop app. Same projects, same plugins, same Chrome sessions, just operated from your phone. These two updates are designed to be read together: the Codex app becomes the host, and Chrome plus mobile become the surfaces.
The growth context OpenAI quoted at launch: Codex now has more than 4 million weekly active users, up 8x since the start of the year. Whether that number is generous on definitions or not, the direction is unambiguous. Codex is the product OpenAI is investing in for developers.
Install: the four steps that actually work
Despite a fair amount of confusion in the first week (more on that below), the working path is short:
- Open the Codex desktop app and go to the Plugins menu
- Click Add on the Chrome plugin
- Follow the prompt — it opens the Codex extension page on the Chrome Web Store and installs version 1.1.4
- Approve Chrome’s permission prompts, then verify the extension shows Connected in Chrome’s toolbar
The non-obvious part is step 1. You install the extension from inside the Codex desktop app, not from the Chrome Web Store directly. The extension exists on the store, but it will not function until the desktop app handshakes with it. Several developers in the first week tried the reverse order and got an extension that did nothing.
If the Chrome plugin does not appear in your Plugins menu, you are most likely in an early-rollout cohort that has not been flipped on yet. Update the Codex desktop app to the latest release, sign out and back in, and check again. The plugin is also gated by region — see the EU/UK section below.
What the extension can actually do
The marketing line is “Codex works in your browser.” That is true but underspecified. Here is the concrete capability list:
- Drive sites where you are signed in. The headline use case. Gmail, Salesforce, LinkedIn, Notion, internal SSO-protected tools, anything your normal Chrome profile can already see.
- Read across multiple tabs. You can ask Codex to compare two product pages, reconcile a spec doc with a ticket, or pull context from a Linear board while writing the code that closes the ticket.
- Use Chrome DevTools. The extension exposes the page debugger, which means Codex can inspect a failing element, read console errors, and check network requests instead of guessing.
- Run in parallel without stealing focus. Background tab operation is the design choice that makes this tolerable. Earlier browser agents would seize the foreground window every few seconds. This one does not.
- Reference your browsing history. Scoped per-request, with a confirmation prompt. Useful for “find that article I read last Tuesday about X” style queries, less useful for anything else.
The capability that quietly does the most work is multi-tab context. A surprising fraction of real coding tasks are “look at this Stripe doc, this internal endpoint, and this GitHub PR all at once, then write the integration.” Before the extension, you had to paste all three into the prompt. Now Codex reads them where they live.
The permissions model — what you are actually agreeing to
The Chrome Web Store listing requests the following permissions:
- Access the page debugger
- Read and change all your data on all websites
- Read and change your browsing history on all your signed-in devices
- Display notifications, manage bookmarks, handle downloads
That is a broad surface. The mitigations are two:
- Per-site confirmation is on by default. Every new domain Codex tries to open triggers a prompt. Approving means “this site, this task.” Approving with always-allow turns the prompt off for that domain forever.
- Allowlist and blocklist apply on top. You can pre-approve a small set of sites and block others outright. Codex respects these even when the model has the technical permission to navigate further.
The configuration I would recommend for a developer using this on a work laptop:
- Keep per-site confirmation on
- Always-allow the two or three sites you are actively automating (your CRM, your monitoring dashboard, your docs)
- Blocklist anything financial, anything HR-related, and anything where a mistake would be expensive
Treat the extension the way you would treat handing a junior engineer your laptop. Useful for clearly scoped work, not for “go figure out what to do.”
Where it fits: three real use cases
The places I have actually seen this earn its keep in the first week:
1. CRM and inbox triage. “Look at the three Salesforce opportunities flagged this week, pull the last email thread from each, and draft a follow-up that references the latest call notes.” Pre-extension, you would do this by hand or wire up the Salesforce and Gmail APIs. With the extension, Codex drives the actual web app. Slower per click, but zero auth setup.
2. Web app debugging with real session state. A bug that only reproduces when logged in as a specific user role. The extension can open the staging environment, sign in (you are already signed in), click through the broken flow, read the console errors via DevTools, and propose a fix in your local repo. The headless-browser version of this workflow has always been technically possible and practically miserable to set up.
3. Cross-tab research. “Read this OpenAI blog post, this Anthropic doc, and this benchmark page, then draft the migration plan.” Three tabs Codex reads in place. The output is grounded in the actual current text of each page, not in the model’s training data.
For headless code-only tasks — refactors, file operations, terminal commands — keep using Codex CLI. The Chrome extension is the wrong tool for those. If you want the full picture on agent comparison, the coding agents head-to-head article covers where each one fits.
Where it fits in an ofox-based stack
Quick honest framing: the Chrome extension is bound to the Codex desktop app, which authenticates with your OpenAI account. It does not currently honor an OPENAI_BASE_URL override, so you cannot route the Chrome extension’s traffic through an aggregator like ofox.ai. That is an OpenAI direct billing line.
What you can do is split the surfaces:
- Codex Chrome + Codex desktop app → OpenAI direct, for the signed-in browser tasks
- Codex CLI → routed through ofox via
OPENAI_BASE_URL=https://api.ofox.ai/v1and your ofox key, for the headless terminal work
This split is not a workaround. It is the cleanest way to think about it. The Chrome extension’s value is access to your Chrome profile, and the routing layer cannot help with that. The CLI’s value is portable, scriptable code editing, and the routing layer can give you GPT-5.3 Codex pricing at $1.75 / $14 per million input/output tokens on ofox, plus the ability to A/B against Claude or Gemini through the same key. The AI API aggregation guide explains the routing pattern.
For setup of the routing side, the Codex CLI configuration guide walks through the environment variables. The Codex installation guide covers the desktop app install if you have not done that yet.
What is still broken in week one
This is week one of a major launch. Things to know:
- Plugin missing from directory. The most common report — the Chrome plugin does not appear in the Codex app’s Plugins menu. This is staged rollout. If you are not in the cohort yet, updating the app and re-authenticating sometimes flips it on. If it does not, wait — OpenAI is widening the rollout day by day.
- Extension install fails with a generic error. Usually a stale Codex app version. Update the desktop app to the latest release before trying again.
- EU and UK are excluded. OpenAI confirmed the extension is not available in those regions at launch and has not committed a timeline. Codex CLI and the desktop app’s non-Chrome features still work; the bridge specifically is held back.
- No Chromium-based browser support yet. Edge, Brave, Arc, Opera. All unsupported at launch despite being Chromium. GitHub issue #22638 is the tracking thread. OpenAI has acknowledged but not committed to a date.
- Performance varies with tab count. Background-tab operation is the design, but a Chrome profile with 80 tabs open will slow Codex meaningfully. If you live with a lot of tabs, run the extension in a dedicated Chrome profile.
Where this goes next
The Chrome extension plus the May 14 remote-connections feature read like a two-step roadmap. Step one: make Codex able to drive your real browser. Step two: make Codex remote-accessible from your phone. Combined, the product is a desktop-anchored agent that you can reach from anywhere and that has your actual login state. That is a meaningfully different shape from “an LLM in a chat box.”
For developers, the practical bet for the next quarter is to keep your code workflow in CLI (routed through whichever provider you trust) and to start moving your web-app tasks, one site at a time, into the Chrome extension. CRM updates, support triage, internal-tool automation. Start with the allowlist set to one domain. Add the next one only after the first stops surprising you.
The right way to onboard the Codex Chrome extension is the same way you onboard a junior engineer: one allowed site at a time, with confirmation prompts on, and the blast radius scoped to things a mistake cannot break.
If you want to see how the Codex Chrome extension compares against alternatives in a broader coding stack, the best LLM for coding ranked by real use piece covers model selection, and the coding agents head-to-head covers tooling.
Cited sources: OpenAI Codex Chrome extension docs, Codex changelog, Chrome Web Store listing, GitHub issue #22638 on Chromium support.
