Google turned Antigravity into a full agent-first development platform at I/O 2026. Antigravity 2.0 is now a standalone desktop application built entirely around agent orchestration — plus a CLI, an SDK, Managed Agents in the Gemini API, and enterprise support via the Gemini Enterprise Agent Platform.
## The four surfaces
Desktop app: a central home to orchestrate multiple agents running tasks in parallel, with dynamic subagents, scheduled background tasks, and integrations across AI Studio, Android, and Firebase. CLI: a lightweight terminal surface for creating agents without a GUI. SDK: programmatic access to the same agent harness that powers Google’s own products, hostable on your own infrastructure. Managed Agents: one Gemini API call spins up an agent that reasons, uses tools, and executes code in an isolated Linux sandbox.
## The scheduled-tasks angle
Antigravity 2.0 ships scheduled tasks — define a task that invokes an agent automatically in the background, converting the agent from a single-turn tool into a persistent automation pipeline. Native voice command support is in too.
## Why it matters
This is Google’s direct play against Claude Code, Cursor, and the OpenAI Agents SDK. The “Managed Agents in one API call, isolated Linux sandbox” feature targets the exact pain point that’s been killing headless agent deployment — infrastructure isolation without DIY sandboxing. The agent-platform war just got a third serious entrant.

Leave a comment