OpenAI just dropped a major Codex update, one hour after Anthropic's Opus 4.7. Whats new: background computer use on macOS (Codex clicks and types on your Mac while you keep working), in-app browser, image generation via gpt-image-1.5, persistent memory, long-running
AGENTS
-
Codex AI Agent Transforms Computer Workflow and Productivity
By
–
Codex has completely changed how I work. There’s almost no task I start without it now. What started as a coding agent is becoming a teammate for almost everything you do on a computer. Read more on our blog:
-
Codex Releases Computer Use, Browser, and Image Generation
By
–
Top things we released in Codex today: > Computer use on Mac: Codex can see, click, and type across apps
> In-app browser for faster frontend, app, and game iteration
> Image generation with gpt-image-1.5
> 90+ new plugins across tools like JIRA, CircleCI, GitLab, Microsoft -
Codex Expands with Computer Use and Plugin Integration
By
–
Big day for Codex!
— Romain Huet (@romainhuet) 16 avril 2026
Codex can now work across more of your computer and more of your tools.
Features many of you have been asking for are here: computer use, in-app browser, 90+ plugins, image generation, memory, thread automations, and more.
Can’t wait to see what you build! pic.twitter.com/TD2plrlHpMBig day for Codex! Codex can now work across more of your computer and more of your tools. Features many of you have been asking for are here: computer use, in-app browser, 90+ plugins, image generation, memory, thread automations, and more. Can’t wait to see what you build!
-
Generative AI Tech Stack: Six Layers Powering Autonomous Agents
By
–
The Generative AI ecosystem is evolving into a full tech stack — powering autonomous AI agents.
From infrastructure and LLMs to RAG pipelines, agent behaviors and orchestration layers, this framework shows the 6 layers driving next-gen AI systems. Credit: @goyalshalini #AI -
Tweet sent by Codex via Computer Use automation
By
–
This tweet was sent by Codex via Computer Use pic.twitter.com/UyxAw6MVj0
— Vaibhav (VB) Srivastav (@reach_vb) 16 avril 2026This tweet was sent by Codex via Computer Use
-
Codex macOS Computer Use: AI Agent Automates App Workflows
By
–
With computer use on macOS, Codex can now use any app by seeing, clicking, and typing with its own cursor.
— OpenAI (@OpenAI) 16 avril 2026
It runs in the background without taking over your computer, working on tasks like frontend iteration, app testing, or any workflow that doesn't expose an API. pic.twitter.com/iO9iubLZX9With computer use on macOS, Codex can now use any app by seeing, clicking, and typing with its own cursor. It runs in the background without taking over your computer, working on tasks like frontend iteration, app testing, or any workflow that doesn't expose an API.
-
AI Agent with Mac App Integration and Task Automation
By
–
Codex for (almost) everything.
— OpenAI (@OpenAI) 16 avril 2026
It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks. pic.twitter.com/UEEsYBDYfoCodex for (almost) everything. It can now use apps on your Mac, connect to more of your tools, create images, learn from previous actions, remember how you like to work, and take on ongoing and repeatable tasks.
-
Evaluator Templates for Production Agent Deployment
By
–
We built evaluator templates around the most common eval requirements when putting agents into production. 30+ customizable templates are now available, including: LLM-as-judge evaluators with tuned prompts Rule-based code evaluators Also available in openevals v0.2.0,
-
LangSmith Launches Startup Program with AI Agent Tools
By
–
LangSmith for Startups gives early stage teams the tooling and community they need to iterate faster and win bigger.
— LangChain (@LangChain) 16 avril 2026
Observe, evaluate, and deploy your agents — now with free credits to help you get started.
Our Scale program offers:
– $10,000 in LangSmith credits
– Exclusive… pic.twitter.com/6r2u8OIL4cLangSmith for Startups gives early stage teams the tooling and community they need to iterate faster and win bigger. Observe, evaluate, and deploy your agents — now with free credits to help you get started. Our Scale program offers:
– $10,000 in LangSmith credits
– Exclusive