The perfect way to start the #WebML wave by introducing it at perhaps the most prestigious JS Conference. We are in a JavaScript<3 Machine Learning space and i am glad to be a part of it. @jsconf_india #MadeWithTFJS

Out now @elonmusk

The @e2b + Docker + @GroqInc hackathon just wrapped - and the submissions went beyond our expectations! We used real agents, real tools, built in secure sandboxes. Congrats to our winners for pushing the bounds of what agentic AI can do. See what they made →

We’re bringing a specialist in browser-based AI agents! Join our workshop with @HowDevelop to explore booming AI, from LLMs and RAG to tool-using agents. Learn to build JS-powered agents in the browser or cloud. Register now: https://t.co/faaVtt4rtS #singapore

Introducing Claude Opus 4.5: the best model in the world for coding, agents, and computer use. Opus 4.5 is a step forward in what AI systems can do, and a preview of larger changes to how work gets done.

Configuring MCP servers - especially with OAuth - can get messy fast. This demo shows an agent handling it with `mcp-find` + `mcp-add`. Let agents guide the setup. 🔗 https://t.co/d0Aw2II9Gf #Docker #MCP #OAuth #AIagents #DevTools #AgenticAI #LLM

Everyone needs a winter in Lake Tahoe

This week we introduced @antigravity, a new agentic development platform where agents operate across the editor, terminal, and browser. Check out this tutorial to get started. Highlights: 00:00 Overview 00:44 Agent Manager, editor, browser 01:48 Agent-assisted development 02:15

✨This year Google also launched LiteRT.js - a new client side Web AI runtime that can run machine learning models right in the browser! To test and learn the ropes I found a depth estimation model from @Qualcomm that runs in real time on my old NVIDIA 1070 GPU in real-time

Leaving this here for you to be part of the @GitHubCommunity's biggest Delhi event 🌟 We just crossed 7.1k+ members, since we started 1.5 yrs ago. Thanks @kong @juhi_singh15 for their support 🤝

we just raised another $25M after 10x'ing our ARR in 5 months. the crazy part is this almost never happened. 17 years ago, I watched Iron Man as a 10-year-old kid in Delhi. that night, I pulled my first all-nighter teaching myself to code. not because I wanted to build apps or

Exciting expansion! @Waymo now serves the whole SF Bay Area Peninsula from SF to San Jose and is taking riders on freeways. https://t.co/fNgqQtHB7b

Google Antigravity has a lot of features, both familiar and new. Kevin from our engineering team walks through the basics in our official 101 tutorial. Link in 🧵

Mandatory bi-annual @CloudNativeFdn @KubeCon_ headshots at KubeCon NA honing a wonderful @kubernetesio Jersey and my favorite @Docker Captain's Jacket 😎

Quick run through of @googledevs new code editor - Antigravity with @gemini 3 Pro! First impressions - The UI looks sleak, the agent planning mode and capability to run background agents is great. And the ability for the agents to see the web will be a massive help when running

Introducing Gemini 3 Pro, the world's most intelligent model that can help you being anything to life. It is state of the art across most benchmarks, but really comes to life across our products (AI Studio, the Gemini API, Gemini App, etc) 🤯

Glad to be invited to the @Columbia_Biz Columbia Business School to conduct a technical session on Agentic AI for businesses and how MBA students can adopt Agentic AI using @awscloud Bedrock models and @n8n_io

When @Cloudflare goes down 🫠 it brings the entire web down as well - Cloudflare Global Network experiencing issues

The role of memory in any AI application or agent cannot be overemphasised. This is why AI can remember users, learn from past interactions, and make better decisions over time. Without memory, every interaction starts from zero. With memory, AI becomes truly intelligent. Check