Meta quietly launches vibe-coded gaming app Pocket
Meta has quietly launched Pocket, an experimental AI app that lets users generate and share interactive mini games using text prompts.
Make your prediction
Will Meta's Pocket app appear on the Apple App Store by July 10, 2026?
Resolves by Jul 10, 2026
Your prediction
50% · 50/50 coin flip
NOYES
Get smart on it
Meta has launched a gaming app called Pocket that allows users to generate small interactive apps and games using AI prompts. The app resulted from Meta's acquisition of a team behind a similar platform called Gizmo earlier in the year, and it features both creation tools and a feed where users can discover and play games made by others. This launch represents Meta's broader effort to make AI creation tools mainstream, following earlier releases of AI image and video generation tools across its platforms. Since Meta has not officially announced the app, it appears to still be in an early experimental phase.
Related news
Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox
WebBrain is a free, open-source browser agent for Chrome and Firefox. It reads pages, extracts data, and automates multi-step tasks. Unlike most browser AI plugins, it can also run entirely on a local model. It is built by Emre Sokullu and licensed under MIT. The full source lives on GitHub. Run the agent against a local model, and no page data leaves your machine. Connect a cloud API when you want more capability. What is WebBrain? WebBrain lives in your browser’s side panel
RAG-Anything Tutorial: Build a Multimodal Retrieval Pipeline for Text, Tables, Equations, and Images in Colab
In this tutorial, we build a RAG-Anything workflow and use it to explore how multimodal retrieval works across text, tables, equations, and images. We start by preparing the Colab environment, installing the required packages, and securely entering our OpenAI API key at runtime to keep the notebook practical and safe to run. We then create a synthetic multimodal report, generate a chart and PDF, convert the content into RAG-Anything’s direct content_list format, and insert it into the retrieval
