X：Google AI for Developers

Introducing Magenta RealTime 2 (MRT2): the live music model you can play as an instrument. MRT2 offers MIDI and prompt controls, and runs natively on a MacBook with <200ms latency. Open weights. Open source inference engine. Suite of apps and plugins. Hear what it can do and try it out for yourself below 🧵 Video

HeyGen + Google DeepMind in LA on June 11 A night of demos, conversations, and people building with agents, multimodal apps, and creative tools Got something interesting? Lightning demo slots are open. luma.com/heygen-xesd

Google I/O showed where AI is headed. Our community spent the weekend building it. Builders gathered in San Francisco alongside @GoogleDeepMind to turn the newest Gemini + Gemma capabilities into working products. From multimodal agents and voice interfaces to long-horizon reasoning systems, teams showed us what’s possible with Gemini 3.5 Flash. The winners: Video

Cosmetic products Promotional with Nano Banana 2 on @itsPolloAI Generate ur product with prompt : ⤵️

Nano Banana 2 really solves text rendering and accuracy. Not a single word in this is wrong. Press and hold to load in 4k!

1) I use "Max concision, reply like a continental open source maintainer", I like it curt 2) For nano banana I found this one that works great for getting landscape architecture-style illos from imagery "Create a masterpiece-level hand-drawn urban planning map based on the provided oblique aerial image. The style should merge technical accuracy with artistic cartography. Era: 1940s Visual Style: Ink and watercolor wash aesthetic, but with the precision of a CAD drawing. Vibrant but natural color palette. Detailed Elements: Buildings: Hand-inked outlines with a slight bevel effect for dimensionality. Nature: Trees should be represented by individual distinct circular canopies for street trees, and textured green washes for parks. Water: Watercolor texture blue with defined banks. Roads: Clearly defined clean paths, varying in width based on the satellite image prominence. Composition: High level of detail, covering all semantic classes (sidewalks, swimming pools, medians). The result should look like a finalized illustration ready for print. Zero text on final product

While everyone's hyping effects, Nano Banana Pro in LTX solved character consistency across angles. → Native 4K → Native lipsync NB PRO 🤝 LTX-2

One prompt: "generate a high resolution image about a cell." This is what Nano Banana 2 (@GoogleDeepMind) rendered. Nucleus, mitochondria, Golgi apparatus, cytoskeleton — all anatomically correct, all stunning.

Gemini 3.5 flash + Gemini managed agents api just audited a real megatron-lm ci failure inside Eigent. root cause in minutes! watch the handoff: coordinator agent plans the audit, developer agent loads the ml-failure-audit skill and gathers the evidence, then gemini agent steps in as a remote sub-agent for the heavy reasoning. gemini managed agents api and gemini 3.5 flash now live on our open-source cowork Eigent! @googleaidevs @GoogleAIStudio Video

🚀 The team at @Google just released the Agents API, a service for building and running custom agents inside a sandboxed Linux environment, and we built a template that gives these agents access to LlamaParse / LiteParse, enabling them to process unstructured documents automatically 📄⚡ Here’s how it works: 🔹 Configure a Git repository where data and outputs will be stored 🔹 Clone the repository into the agent sandbox 🔹 Install the LiteParse CLI, the LlamaParse SDK, and agent skills to use both 🔹 Prompt the agent with a task and watch it process documents autonomously 🤖 The result? An agent that can work directly with messy, real-world documents using LlamaParse and LiteParse within Google’s new agent runtime. Check out the GitHub repository: github.com/run-llama/antigra… Get started with LlamaParse: cloud.llamaindex.ai/signup Video

The scariest bug from a coding agent isn't the one that crashes. It's the one that runs cleanly, passes tests, and quietly produces wrong results. So we built one on @Antigravity's Gemini Managed Agents API to hunt them. Give it a repo. Get back the bugs that passed review.