Captain's log, stardate d650.y41/AB
OpenAI has officially launched the ChatGPT App Directory, opening a new distribution channel for developers to publish applications that run directly inside ChatGPT.
Starting now, developers can submit their ChatGPT apps for review. Once approved, apps become discoverable in a dedicated directory, allowing users to search for and access apps without leaving ChatGPT. This marks a clear shift from experiments like plugins and GPTs toward a more structured and scalable app ecosystem.
Apps inside ChatGPT are built using the new Apps SDK. The SDK is designed for chat-native experiences and focuses on tightly scoped use cases rather than generic assistants.
To help developers get started, OpenAI provides:
Apps are submitted through the OpenAI Developer Platform, where developers can:
OpenAI has also updated its submission guidelines, detailing what they evaluate around quality, UX, safety, privacy, and transparency.
The App Directory turns ChatGPT into a new distribution and monetization channel for businesses. Companies can now offer their platforms and services directly inside ChatGPT.
This makes it dramatically easier for end users to discover, try, and use services in a context they already trust and use daily. As discovery, monetization, and distribution evolve, businesses gain a new way to increase reach, engagement, and revenue.
This launch validates our focus and direction. GPTApps is an agency dedicated to designing and building applications specifically for ChatGPT and its app ecosystem.
We have already developed several ChatGPT applications and look forward to publish our first apps in the ChatGPT marketplace. This marks the beginning of a new category of software, and we are excited to help businesses turn their services into high-quality, discoverable ChatGPT apps.
This scam targets dev agencies and freelancers via contact form enquiries with large budgets, then funnels victims to a fake Google Sites page that serves malware via a fake certificate installer (.dmg).
Read full article
AI agents often over-abstract coincidental duplication, creating fragile architectures that increase cognitive load and technical debt. Prioritizing clear domain boundaries over rigid DRY principles is essential for keeping codebases maintainable for both humans and AI.
Read full article
After starting with Cursor in 2024, we are now standardizing on Claude Code for our 2026 agentic strategy. This move marks our official shift from writing code to defining problems and steering the process.
Read full article