OpenAI Announces the Codex Micro: a Work Louder kbd-1.0 Collaboration for Codex Workflows
OpenAI Developers highlighted the Codex Micro, a $230 Work Louder co-lab keyboard accessory with RGB agent-status keys and dedicated controls for common Codex actions.
OpenAI Developers announced the Codex Micro, a Work Louder co-lab hardware accessory aimed at bringing Codex workflows closer to the keyboard (OpenAI Developers on X).
According to OpenAI’s product page, the Codex Micro is “your command center for agentic work” and is “designed with Work Louder” as the “kbd-1.0-codex-micro” (OpenAI Supply Co. x Work Louder).
What it is
OpenAI positions the device as a way to keep agent work visible and controllable from physical controls, including:
- “Keep active chats close” (OpenAI Supply Co. x Work Louder)
- Using live RGB feedback to “spot what every agent is doing” (OpenAI Supply Co. x Work Louder)
- Mapping “most-used Codex actions to tactile controls” (OpenAI Supply Co. x Work Louder)
Key features (from OpenAI)
| Feature | What OpenAI says |
|---|---|
| Agent status at a glance | “Each Agent Key lights up with a live RGB status from Codex,” showing whether an agent is “thinking, running, waiting, or done.” (OpenAI Supply Co. x Work Louder) |
| Workflow triggers | “Flick the joystick to launch common Codex workflows like reviewing a PR, debugging an error, or refactoring code.” (OpenAI Supply Co. x Work Louder) |
| Core action shortcuts | “Command keys give your most-used actions a dedicated shortcut: accept, reject, push-to-talk, start a new chat, and more.” (OpenAI Supply Co. x Work Louder) |
| Reasoning dial | “Turn the dial to adjust reasoning level in the moment.” (OpenAI Supply Co. x Work Louder) |
Price and compatibility
The OpenAI store page lists the Codex Micro at $230.00 and notes Bluetooth / USB-C connectivity with Mac / Windows compatibility (OpenAI Supply Co. x Work Louder).
What to do next
If you use Codex heavily, consider whether dedicated, tactile shortcuts and an always-on “agent status” view would fit your workflow -- especially if you frequently bounce between multiple chats or agent runs (OpenAI Supply Co. x Work Louder).
Read next
Related coverage- OpenAI
OpenAI Models and Codex Are Coming to Google Cloud
OpenAI and Google Cloud plan to make OpenAI frontier models and Codex agentic workflows available in Google Cloud's Model Garden. The announcement says frontier models can be purchased through Google Cloud Marketplace and general availability is planned in the coming weeks, but it does not name the models or a launch date.
- OpenAI
OpenAI Adds 12-Hour Prompt Caching to the Responses API
OpenAI added an optional 12-hour prompt-cache lifetime to the Responses API for GPT-5.6 and later. Developers can keep matching prompt prefixes eligible for cached-input pricing across longer gaps by setting `prompt_cache_options.ttl` to `12h`; the default remains 30 minutes. The longer cache write costs more, so the tradeoff depends on reuse.
- OpenAI
OpenAI Shares a PHP Version Checker and Codex Skills
OpenAI has published a PHP Version Checker repository with Codex skills for identifying PHP versions that may need security updates. The checker reads the version a website advertises in its headers or a local PHP installation reports and compares it with the upstream fixed releases from the October 21, 2026 PHP advisory. It is a triage aid, not proof that a system is patched or secure.
- OpenAI
OpenAI Reports Stronger Coding Results in COBOL, Fortran, and Visual Basic
OpenAI says its latest models improved on two software-engineering evaluations for low-resource languages. On MultiLangBench, GPT-6 Astra averaged 87.4% at maximum reasoning effort across 20 programming languages; on a COBOL migration test, GPT-6.1 Sol scored 86.6% at low reasoning effort. These are OpenAI-designed evaluations, not a guarantee of production migration quality.
