Vivold Consulting
Other

Antigravity 2.0: a platform to orchestrate autonomous AI agents

Google's Antigravity 2.0 turns its coding tool into a hub for managing fleets of AI agents

Key Insights

Google expanded Antigravity, its agent-first development platform, beyond coding into a system for developing and managing cohorts of autonomous AI agents - headlined by Antigravity 2.0, a standalone desktop app that acts as a central home for orchestrating agents across tasks. It runs on a specially optimized version of Gemini 3.5 Flash that Google says is 12x faster than other frontier models. Users could start trying the experience at I/O.

Stay Updated

Get the latest insights delivered to your inbox

A coding tool becomes an agent control center

Google used I/O 2026 to broaden Antigravity, its agent-first development platform, from a coding environment into a place to build and manage whole cohorts of autonomous agents.

What changes with 2.0

  • Antigravity 2.0 is a new standalone desktop application that serves as a central home for agent interaction, where developers - and others - can orchestrate agents for many kinds of tasks rather than just code.
  • It's powered by an even more optimized build of Gemini 3.5 Flash that Google says runs 12x faster than other frontier models, beyond the 4x of the standard Flash.
  • It's the same harness behind Google's consumer agent, Gemini Spark, and behind new agentic capabilities in Search, making it a connective layer across Google's agent strategy.

Why it matters

Antigravity is increasingly central to how Google itself builds - the company credits a reimagined version of it, paired with 3.5 Flash, for dramatically accelerating internal development, with its AI developer tools now processing more than three trillion tokens a day. By packaging agent orchestration into a standalone app, Google is betting that managing fleets of agents - not just prompting a single model - becomes a core developer workflow. Users could begin sampling the experience during I/O.

More in Other

All Other stories

Coinbase for Agents: Automating portfolio trading with AI

Coinbase for Agents connects AI agents to live financial execution, letting them trade, pay, and rebalance within user-defined limits straight from a portfolio. It offers a CLI path for dev tools like Claude Code and Codex and a Model Context Protocol path for web agents like ChatGPT and Claude, with agents confined to isolated portfolios and run through Know-Your-Transaction checks. It completes a stack that began with AgentKit (2024) and the x402 agent-payments protocol, turning LLMs from advisors into actors.

Microsoft's open source tools were hacked to steal passwords of AI developers

Microsoft disabled dozens of its open-source GitHub projects - at least 70 - after hackers reportedly injected password-stealing malware into the code. Many affected projects relate to Azure and tools used with AI coding apps like Claude Code, the Gemini CLI, and VS Code, with credentials stolen when developers opened the compromised tools. It's reportedly Microsoft's second such breach in weeks, described as a re-compromise of a previously hit project.

VHA Deploys Salesforce-Powered Agentic Operating System, Saving Thousands of Staff Hours for Front-Line Veteran Care

The Veterans Health Administration (VHA) has implemented a Salesforce-powered agentic operating system, resulting in significant operational efficiencies. Key outcomes include: - Transitioning from static reporting to automated problem-solving, eliminating administrative silos. - Freeing thousands of staff hours, allowing more focus on direct Veteran support. - Creating a connected performance management layer, enhancing care delivery across facilities.