New post on the OpenAI Developer Blog: how we use skills for open-source maintenance, from planning and coding to testing and release-readiness checks with GitHub Actions. Hope it's useful for your projects too 🙌 https://t.co/KkoTaOUutn
Turns out building with @ChatGPT Sites is pretty addicting. So is clicking cookies. 🍪
I made a little demo that does both, with a database and an MCP server so ChatGPT and Codex can join in.
Come hang out. I hope it gives you an idea for something fun to build.
Chapters:
00:00 A cookie clicker for humans and AI
00:27 The prompt I started with
00:41 Saving clicks in a database
01:16 Adding MCP tools
01:29 MCP in plain language
02:09 Testing with MCP Inspector
03:11 Asking ChatGPT for the click count
03:40 Clicking a cookie with Codex CLI
04:10 What will you build?
Great to be in Tokyo with @gabrielchua and @seratch for OpenAI DevDay Exchange 🇯🇵
Excited to share what we’ve been building with the developer community here!
よろしくお願いします!
Great to be in Tokyo with @gabrielchua and @seratch for OpenAI DevDay Exchange 🇯🇵
Excited to share what we’ve been building with the developer community here!
よろしくお願いします!
@AlexRouteAPI This timeout applies only to individual attempts; there is currently no timeout for the entire run. We may consider adding one in the future. Thanks for sharing this feedback!
Another OpenAI Agents SDK update:
This has been a long-awaited feature! You can now set a timeout for each model call, and the retry mechanism also handles timeouts.
See https://t.co/8igDjcbwgS for details.
I've been running this image generation code example over the past 13 months to track its behavior: https://t.co/TV2g1sSvLh
The outputs are now dramatically different from what they were back then!
OpenAI Agents SDK for TS now supports Standard Schema.
This means you can use not only Zod, but also any other schema library compatible with the spec, such as Valibot.
See https://t.co/Elh5XYJnpk for details! 👋
Writing tests for agent apps built with the OpenAI Agents SDK is now much easier!
You can use the newly added, reusable ScriptedModel utility to mock model calls. See https://t.co/uv7YYmUY1i for details.
Since posting this a week ago, I've continued optimizing the harness to help Codex reach a mergeable state even faster. This really feels like a new era in software engineering.
This repo skill improves my first-pass code (but takes time). If 👍 is hard to earn in GPT-5.6 Sol reviews, try something similar.
https://t.co/iobwQxVk3l
Sorry this took so long. We received requests for React Native support in the same month that we released OpenAI Agents SDK TS, and it's finally here!
Here's a demo app showing how to use the runtime shim: https://t.co/l8iuD80Tj6
This repo skill improves my first-pass code (but takes time). If 👍 is hard to earn in GPT-5.6 Sol reviews, try something similar.
https://t.co/iobwQxVk3l
Helped enthusiastic Codex users with their Build Week submissions this morning! It’s a public holiday here in Japan, but they were up early building! 🚀🚀🚀
You might have noticed that the multi-agent feature was also released in beta for the Responses API with GPT-5.6 models: https://t.co/ER717WM9OF
It's now supported in our Agents SDKs as well!
https://t.co/GYlD1BFdwl
I was just thinking back to how tough it was to complete this refactoring work six years ago: https://t.co/yudmfQsAob
Now that we have Codex, doing something similar in 2026 would be drastically easier. What a great time to be a software developer.