Developer’s Guide to AI Agent Protocols

NASA’s X-59 is helping the nation celebrate the 250th anniversary of its independence with an update to its livery – its official paint job and insignia. The one-of-a-kind research aircraft is the centerpiece of NASA’s Quesst mission to demonstrate technology to fly supersonic, or faster than the speed of sound, without generating loud sonic booms. […]

Google Cloud has introduced the Agents CLI, a specialized tool designed to bridge the gap between local development and production-grade AI agent deployment. The CLI provides coding assistants with machine-readable access to the full Google Cloud stack, reducing context overload and token waste during the scaffolding process. By streamlining evaluation, infrastructure provisioning, and deployment into a single programmatic backbone, the tool enables developers to move from initial concept to a live service in hours rather than weeks.

Gemini CLI introduces Plan Mode, a read-only environment for analyzing codebases. It helps developers refine strategies without risking accidental execution.

A new server connects AI agents to Google Colab, aiding developers in prototyping. This benefits those working with AI agents like Gemini CLI and Claude Code.

Developers can create a smart financial assistant using LlamaParse and Gemini 3.1 to extract data from complex documents. This helps transform unstructured financial data into readable insights.

Developers can streamline motion-controlled game development using Gemini and MediaPipe tools. This workflow helps create responsive gameplay with low-latency models.