OpenAI adds AI-generated pet overlays to Codex coding assistant
OpenAI added optional AI-generated pet companions to its Codex coding assistant. The floating overlays notify developers when Codex completes tasks or needs input, eliminating the need to switch windows to check status.
OpenAI adds AI-generated pet overlays to Codex coding assistant
OpenAI's Codex coding assistant now features optional AI-generated pet companions that serve as floating overlays, according to the company. The pets display Codex's active status and notify developers when tasks complete or when the tool requires user input.
How it works
Developers can summon or dismiss the companions by typing /pet into the Codex app. The feature includes eight built-in pet options, with the ability to generate custom companions using the /hatch command. Users have already created custom pets including "a cute goblin companion" and recreations of Microsoft Clippy.
The pets function as status indicators, showing what Codex is currently working on without requiring developers to switch away from their active window. OpenAI describes them as "optional animated companions" that do not perform any coding tasks themselves.
Availability and promotion
The feature is available now on both Windows and macOS versions of Codex. OpenAI is running a limited-time promotion offering 30 days of ChatGPT Pro to creators of 10 companion designs the company selects as favorites.
Early adopters have already uploaded multiple custom pet designs, suggesting active community engagement with the feature.
What this means
This update represents a shift toward making AI coding assistants more ambient and less disruptive to developer workflow. By providing status updates through a persistent overlay rather than requiring window switching, OpenAI is addressing a common friction point in agentic coding tools. The customization aspect and community sharing suggest OpenAI is testing more personalization features for developer tools, though the practical utility of animated companions over traditional status bars remains to be proven in production environments.
Related Articles
OpenAI Cuts GPT-5.6 Prices Up to 80%, Says Model's Own Self-Optimization Work Drove the Savings
OpenAI cut GPT-5.6 Luna pricing by 80% to $0.20/$1.20 per million tokens and GPT-5.6 Terra by 20% to $2/$12, while adding a 2.5x-faster mode for Sol at double the price. The company says GPT-5.6 itself rewrote production inference kernels and tuned its own speculative decoding pipeline to enable the cuts.
OpenAI Slashes GPT-5.6 Luna Pricing by 80%, Cuts Terra by 20%
OpenAI cut GPT-5.6 Luna pricing by 80 percent to $0.20 per million input tokens and $1.20 per million output tokens, while Terra dropped 20 percent to $2/$12. The company attributes the cuts to infrastructure efficiency gains and mounting price competition, particularly from Chinese providers.
OpenAI Cuts GPT-5.6 Terra Price 20%, Luna Price 80% Across API and ChatGPT
OpenAI is cutting API prices for its GPT-5.6 Terra and Luna models by 20% and 80%, respectively, compared to prices set earlier this month. The company says the lower costs are also reflected in usage limits for ChatGPT Work and Codex subscribers, though subscription prices remain unchanged.
GitHub Copilot App Adds Stacked Sessions and Pull Requests for Sequential Coding Tasks
GitHub has published a walkthrough of stacked sessions and pull requests in the Copilot app, a workflow feature that lets developers chain multiple AI-assisted coding sessions and PRs together. The post uses a real-world example: modernizing an old codebase.
Comments
Loading...