Reading up on Codex

Semrush charges $139.95/month. Ahrefs charges $129/month. A guy named Ben built the open-source alternative that you can run on your computer. It is called OpenSEO. Enter a competitor's website and it reveals the keywords bringing them traffic, the pages winning those searches, and the backlinks helping them rank. And enter your own site and it tracks rankings, crawls technical problems, reads Search Console, and shows whether ChatGPT or Google AI Overviews mention your brand. Then connect Claude or Codex. Your agent can pull the real numbers, compare opportunities, cluster keywords, and save a strategy back into the dashboard instead of guessing from a prompt. The hosted version starts at $10 a month. The entire codebase is MIT licensed, so you can also self-host it and pay DataForSEO directly for only the data you use. No, it does not magically reproduce every database and advanced feature Ahrefs built over a decade. But it breaks the most important rule of the old SEO market: You no longer need their permission to own the tool.

@ihteshamali

codex' visualization feature got really good.

@steipete

We’re excited to announce the OpenAI Build Week winners 🥁 Meet the builders behind the eight winning projects and see what they shipped with Codex. https://openai.com/build-week

@OpenAIDevs

incredible use of computer history “based on my computer history, what single-use software would make my life easier?” computer history turns your activity across apps and websites into memories and a timeline, so codex can spot repeated workflows and build the little tools that make them easier

@reach_vb

My full interview with Tibo (@thsottiaux) 0:45 Tibo's Lessons from Google DeepMind 4:22 Building OpenAI’s Relentless Culture 7:23 Astra & Next Gen Models 11:18 How Fast AI Changes Developer Workflows 14:27 ChatGPT & Codex Merging 20:25 OpenAI vs. Anthropic 23:37 Why OpenAI Keeps Resetting Limits 30:25 Recursive Self-Improvement 32:00 Dangers That Caused "The Pause" 34:13 Will Ultra Fast Become the Default? 43:20 Why Everyone Needs to Try AI

@MatthewBerman

It's me again. I come bearing great news. First of all, we have hit 20M active users for Codex some time this week. Second of all, this is cause for celebration and during the day we will credit every Codex and ChatGPT Work user with a BANKED reset that you can use at your own leisure. And we will have some other good news later too! Now, on usage limits draining faster, while we're not seeing anything abnormal, we do take it incredibly seriously and there is an ongoing investigation. I will share if we do find anything and my below post is really a clarification on a specific pattern that we did see that I wanted to call out. Go do something amazing today.

@thsottiaux

Everyday conversations just got easier with the new Apple Messages plugin. Search messages, catch up on conversations, draft and send replies—all with ChatGPT on your Mac. Now available in ChatGPT Work and Codex on desktop.

@ChatGPT

What is an obvious thing that we should do with Codex, API or our models that we should just do but haven't yet? What is 100% within reach, but we just seem to be missing?

@thsottiaux

Good moment today to remind everyone to stay frosty with AI. I was working on making a server stoppable via the CLI, and Codex decided the best path forward was to implement an unauthenticated network API to every server to shut itself down. Excellent work. I responded with "I don't know about that." (I usually give more direct feedback but this was so absurd) and it thought for like 20 seconds and responded "Server stopping should not be part of an unauthenticated network API." Yes. lol. By the way, the result I was looking for was that we automatically start a locally discovery Unix-socket bound server so I wanted it to discover that (using prior mechanisms already made) and gracefully stop that. The driver is absolutely accountable here (me). My lazy prompting led AI to think I wanted to be able to stop ANY configured server I was talking to. Shame on me for thinking it was obvious here. But, I also reviewed it and found this idiocy, so, that's where good AI drivers come in. Also me.

@mitchellh

Brent is really pushing the edge of video editing with codex! Give him a follow

@pvncher

The question I get most right now is "what should I turn into an AI agent?" Here is the 5 part test I use (works for Claude/Codex/Grokbot etc): 1. It has a repeated trigger, so the same kind of task keeps happening over and over. 2. The inputs are stable, so the information comes in a predictable shape every time. 3. The tools are clear, so there is a defined set of things it can actually go do. 4. There is a measurable finish line, so you can tell when it is done and whether it worked. 5. There is judgment in the middle, so each run is a little different and needs a real decision made in the moment. The first 4 are really just asking "can this be automated at all?" The 5th is the one that matters, because judgment in the middle is what makes it an agent instead of a simple automation. Once you see it this way, you start spotting agent work pretty much everywhere.

@gregisenberg

Hey @steipete you know I’m the ultimate clawboi - if you want my true competitive analysis openclaw ++ vibes / personality + local device (but tbh other than being cute doesn’t matter w cloud APIs, but we love a Mac mini moment) + hackable + multiplayer use (good in a group chat for slack) + crons - connector / MCP / gog constant death loop and management - maintenance while traveling grokbot @laurenleeplace ++ connector experience + consumer friendliness (AI pilled my very not ai native friend) + bot to bot hand offs - no multiplayer - vibes - opaque - not hackable eve @shardara @cramforce ++ enterprise connectors + easy to collaborate on building the bot + simple framework for config + evals, monitoring etc + I love chatSDK + tool control / approval UI is great - not consumer friendly - not really self service for non eng - vibes but that’s kind of a me problem codex @ajambrosino ++ just the best ++ code code code ++ computer / browser use + vibes are fine - actually hate the connector experience - no multiplayer - no little computer in the cloud hermes - vibes off just can’t do it

@clairevo

Codex and ChatGPT can now understand the context of your recent work. Opt into Computer History to give ChatGPT richer context, so it can pick up where you left off, understand patterns in your work, and suggest skills or scheduled tasks for work you repeat.

@OpenAIDevs

I previously promised a reset for every 1M in additional active users for Codex, until 10M. We blew past that and have been silent since 10M. Little surprise for you tomorrow.

@thsottiaux

Why did you switch to Codex? What do you like about it and what could we improve? Don’t say reset.

@thsottiaux

New native Codex app for Linux looking great on Omarchy. Good job, @OpenAI! We'll have it hosted on the OPR and available for immediate install in Quattro.

@dhh

Spotify has run this exact play before. In March 2020 they open sourced Backstage, the internal portal their engineers built to manage 14,000 software components. It became the industry standard for developer portals. Over 3,400 companies adopted it, including Netflix, American Airlines, and Expedia. Then Spotify built a paid enterprise product, Portal, on top of the free standard they created. Xirp is the sequel, aimed at a bigger prize. Look at what it actually does. Every agent session runs in its own git worktree, so 50+ agents can work on the same codebase in parallel without touching each other. And context lives outside the agent itself, so you can switch from Claude Code to Codex to Gemini mid-project and the full working state carries over. That second part is the whole strategy. Anthropic, OpenAI, and Google are spending billions to make their agent the one your team depends on. Xirp makes them interchangeable. Your dependency moves up a layer, to the environment holding your sessions, your service catalog, and your architectural decisions. Which happens to plug into Portal, the product Spotify sells. The model vendors are fighting to own the agent. Spotify is betting the agent becomes the commodity and the context becomes the product. Last time they made that bet, 3,400 companies took the free version and Spotify sold them the enterprise one. The music streamer from Stockholm is quietly building one of the better dev tools businesses in the industry, and almost nobody noticed the first time.

@aakashgupta

A great way to learn design: Give Codex a well-designed website, ask it to analyze what makes the design great, then ask it to take a complete screenshot of the website & add annotations on the image that breaks down why the design works Learning from examples is always better than learning from theory! And using the annotation method means you don't have to constantly switch between reading the analysis and viewing the artifact

@zarazhangrui

Codex team: If I am in Codex tab and say "schedule this task in the cloud" (it's a task that just uses plugins) is it actually going to schedule it in the cloud or I have to switch to ChatGPT Work to do this? It doesn't seem to work?

@petergyang

Built this tiny app in few hours with Codex, what a time

@tar_uniqueee

Of all the amazing things that AI is enabling, rigging codex to be my personal assistant has become one of the most impactful, examples: 1. returns/warranties 2. selling stuff on fb 3. trip planning 4. shopping 5. real estate prospecting 6. personal finance harness details below:

@BrandonMChu

ok y'all know i love an anti-todo list (stuff AI can take off my plate FOREVER) in this ep of how i ai, @nickbaumann_ shows me all his expert voice + sites + chatgpt work tricks so i can hand even more off to codex jarvis-style voice assistants, lazy prompting, video use cases, yolo computer use -- this ep hits all my faves A huge thanks to our wonderful sponsors: ⚡️ @boltdotnew - turn your idea into a real product:

@clairevo

i've used so many harnesses over the past few months, i'm having trouble remembering *where* i had past conversations. claude desktop *chat*, claude desktop *cowork*, claude desktop *code*, claude code TUI, codex, chatgpt, hermes, openclaw, conductor 😭

@Shpigford

Setting up Fable to use Codex 5.6 Sol as a subagent was the best idea ever—Fable is super great at supervising but pretty slow at executing on its own and Codex is really fast but needs a nanny. Perfect combo.

@SnazzyLabs

Using a generic agent harness (e.g. Codex, Claude, OpenCode) + CLI/MCP is better than "Ask me anything" built-in product chat boxes in every product I've ever tried. A big reason is I can use the latest frontier models, another is mixing more context. Why your box over mine?

@mitchellh

i would kill for this type of view in Codex

@Jaytel

How to code with Kimi K3 (better than Fable and no restrictions) today: - Ask Codex or Claude Code to install OpenCode (yes it will 😂!) - Go to

@levelsio

Choosing GPT-5.6 Sol, Terra, or Luna in Codex

@pvncher

Introducing TogetherLink! An open source CLI to run any open source model inside your favorite coding harness. Run GLM 5.2 directly in Codex and Claude Code.

@nutlope

Codex for finding customers for your startup:

@gdb

I'm open-sourcing my Agent Skills library. 75 skills for Codex, Claude Code, Cursor, and other agents, focused on web design, landing pages, motion, WebGL, UI styles, and assets. A few favorites: - Video to Super Prompt Turns a screen recording of a design, landing page, or animation into a super detailed prompt that Fable 5 can one-shot into HTML. - HTML to Interaction Prompts Takes an existing HTML page, like something built in Aura, and extracts prompts for sections, buttons, animations, WebGL effects, and interactions. - Stitched Full Page Capture Captures the entire landing page, not just the hero, so you can use the full page as a design reference. - Daily UI Inspiration Combines multiple skills into an agent loop that browses the web, captures great landing pages, and turns them into detailed prompt packs. It's free. Fork them and adapt for your own workflow.

@MengTo

If you run this workflow, ask Fable to make codex the workhorse. https://github.com/steipete/agent-scripts/blob/main/skills/codex-first/SKILL.md

@steipete

Headroom -- a lightweight native Mac OS menu bar app for tracking your usage. Shipping tonight/tomorrow so that you can keep eyes on your Fable-filled week ahead. Works for both your subscriptions and API spends. Codex and Claude for now. Free dollars. Fully signed install package will be downloadable from my website. Stay tuned

@kylezantos

After almost every single task, you can ask Codex/Claude: "anything else to cleanup/simplify?" and there will be something to cleanup/simplify. I do this all the time.

@linuz90

My girlfriend couldn’t cancel a hotel reservation today. No cancel button. They weren’t replying on WhatsApp. Since I really didn’t want to call the hotel, I told her to try and just use Codex. 2 minutes later, she came back to me saying that Codex quickly realized there was a basically hidden cancel button on the reservation page (nasty dark pattern), and it just went ahead and canceled for her. It’s a little thing, but there’s so much daily stuff now I’m doing with Codex. Paired with Computer Use and the Chrome integration, it’s really great at a huge range of tasks, so I’m starting to default to it. (this is probably true for Claude as well)

@linuz90

Your favorite Codex shortcuts are getting an upgrade. July 15th.

@OpenAIDevs

How I AI: Using Codex + Claude Code to Prototype Agents

@clairevo

Show Codex a workflow once. Reuse it as a skill. Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request. Codex turns that demo into an inspectable, editable skill. You control when recording starts and stops.

@OpenAIDevs

WTF Is a Loop? Part 2: The 15 Loops People Are Actually Running (and the Commands to Steal Them)

@mvanhorn

5 steps to create amazing videos like the one below from HTML for free: Install @HyperFrames_ in your favorite coding harness (e.g., Codex or Claude Code). Then... 1. Gather your assets Create a project folder and add screenshots, logos, website captures, reference clips, and a frame md to give Hyperframes the raw material for your video. If you have a design md you can convert it to a frame md here:

@petergyang

So I have Codex running on a /goal and it's been working for 2 hours but the problem is it's making alot of wrong assumptions so I have to monitor and steer it constantly. Is this expected? Perhaps I should've had it make a detailed plan first?

@petergyang

Introducing /visual-plan - a skill to generate rich, visual plans for Claude Code and Codex. Plan mode in Claude Code is incredible. But I always find my eyes glazing over when it gives me this huge markdown essay in my terminal. I found I can make much better visual plans with reusable components. So I made a skill called `/visual-plan`. It generates plans as MDX with visual, interactive components. Diagrams, interactive API specs, schema design changes, annotated code, and even pan and zoomable wireframes. So for any UI work, you can look at a wireframe first, comment on it, iterate, and then have the agent work. I’ve found this to be a much more intuitive interface for reasoning about what the agent is doing. It’s somewhat inspired by that popular post about how HTML is better than Markdown. But HTML can be slow and verbose to write. And it doesn’t look good checked into a repo. This has really made me feel like humans and engineering are entering a new abstraction phase, where we reason about things at the plan level. As long as the plan is good, agents are getting more and more reliable at executing on it. Almost to the degree that we trust the C compiler to compile to assembly reliably. Plans are the new intermediate representation. I also made a skill for the reverse of this, called `/visual-recap`. After the agent works, it gives you a recap of everything it did. Same idea: wireframes, interactive API specs and diffs, schemas, annotated code, etc. So now when you’re reviewing what the agent did for you, or looking at a pull request of somebody else’s code, you can see a visual recap instead of just reading a wall of text. It’s all free and open source. You can find it on my GitHub. Will link to it in the reply because we all know how dumb these algorithms are with links.

@Steve8708

Three Ways Codex Can Use a Computer

@jxnlco

anyone built a reliable system/solution for indexing and searching threads across claude code, codex, cursor..etc? All the built-in ones are not that great.

@shadcn

Mastering Codex (Mobile) for Engineering

@Dimillian

I basically never write my own /goal anymore. I ask Codex to write one for itself, and one for each agent it spawns. Like this 👇

@skirano

We heard you wanted to use Codex rate limit resets on your own time. Starting today, we’re rolling out the ability to save rate limit resets to use later. We’re starting Go, Plus, Pro, and Business users with one free reset:

@OpenAI

Here's a simple loop: Tell codex to maintain your repos, wake up every 5 minutes and direct work to threads. That makes it easy to parallelize+steer work as needed. I use a orchestrator skill combined with my triage+autoreview+computer use skills, so some work can land autonomously.

@steipete

We're betting on the next 1B+ users being agents, so we're launching agent signups. Ask your agent to add Firecrawl, instantly claim your API key, then pull web data in seconds. Works with Codex, Claude Code & Grok Build, all powered by auth.md from @WorkOS🔥

@firecrawl