Googleās offline AI app, Copilotās new coding agent, LangGraph orchestration, AutoGPT workflows, and a beginnerās guide to GenAI.
Google quietly released AI Edge Gallery, an experimental Android app (with iOS coming soon) letting users download and run Hugging Face models like Gemma 3n entirely offlineāfor tasks such as chat, image Q&A, coding, and text promptsāpreserving privacy and needing modern devices.
GitHub Copilot now includes a ācoding agentā that, once assigned an issue, launches a secure GitHub Actions environment, writes code, pushes updates to a draft PR, logs its reasoning, and awaits human review. It runs in the background, letting developers hand off routine tasks and focus on highāvalue work.
AutoGPT is a platform that allows you to create, deploy, and run AI agents in order to automate complex workflows.
LangGraph is a framework that provides low-level orchestration for building, managing, and deploying long-running, stateful agents. It is already being used by companies like Klarna, Replit, and more. It currently supports JS and Python.
DeepSeek-R1-0528 has been released and aims to take on OpenAI o3 and Google Gemini 2.5 Pro. It has improved benchmark performance, enhanced frontend capabilities, reduced hallucinations, and supports JSON output & function calling.
A comprehensive course from Microsoft that includes 21 lessons aimed at teaching everything you need to know to start building GenAI apps.
A curated weekly roundup of AI news, tools, and breakthroughs to stay ahead of the curve in a fast-moving industry.
Curated by devs, for devs. Helping 400+ developers stay ahead of the AI curve.