OpenAI and Work Louder have unveiled the Codex Micro, a $230 hardware controller that lets developers manage AI agents using joysticks and a rotary dial instead of typing commands.
The device's six keys display real-time RGB feedback to show each agent's status, while the joystick triggers workflows like code reviews and debugging, and the rotary dial controls how much compute the model spends on a task.
The device is currently out of stock with limited quantities.
What happened
OpenAI and keyboard maker Work Louder launched the Codex Micro, a $230 hardware device that replaces typing commands with joysticks, a rotary dial, and six programmable keys that light up in real-time to show each agent's status (thinking, working, waiting for input, or done).
Why it matters
Developers managing multiple AI agents currently switch between chat windows and type commands repeatedly; this device consolidates those interactions into a single physical interface, allowing the joystick to trigger workflows like code reviews and debugging, while the rotary dial adjusts reasoning compute levels per task.
What to watch
The Codex Micro is currently out of stock with limited quantities available; it connects via Bluetooth or USB-C and works on Mac and Windows, with full key remapping through ChatGPT Codex and Work Louder's Input software, which supports six programmable layers and 32 swappable icon keycaps.
Ask the AI about this article →
The Codex Micro addresses a friction point in agent-based workflows: developers currently context-switch between chat interfaces and manual typing to command and monitor multiple AI agents. By consolidating status feedback (via the six illuminated keys) and input mechanisms (joystick, dial, keys) into a single device, the hardware reduces cognitive load and typing overhead. The real-time RGB status indicators—showing thinking, done, waiting for input, or error states—make agent activity visible at a glance, while the rotary dial's control over reasoning compute levels gives developers a tactile way to tune inference behavior without opening settings menus. The integration with ChatGPT Codex and Work Louder's programmable software ecosystem (six layers, 32 icon keycaps) positions the device as a customizable hub for multi-agent development workflows rather than a one-size-fits-all peripheral.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Israeli startup DataAgent Ltd
SK Hynix presented a custom HBM concept at SEMICON Taiwan 2026, where compute functions are placed in the base…
Nvidia reported earnings that were both remarkable and boring, reflecting its focus on avoiding a consolidated…
Anthropic has agreed to a $35bn cloud-computing contract with Lambda, a Nvidia-backed cloud provider
The Supreme Court of Japan has included about ¥60 million in its fiscal 2027 budget request for AI-related exp…
The Consumer Affairs Agency said Tuesday it will use generative AI to analyze about 900,000 annual consultatio…
