Google Antigravity 2.0

Orchestrate multi-agent workflows from a desktop app

Task Management

Developer Tools

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉

What stands out is how the agent works across the editor, terminal, and browser in one loop rather than just suggesting code and leaving execution to you. Used it to debug a college project under a tight deadline and it caught issues I'd been staring at for hours.

The "sit in the loop: prompt, wait, respond, repeat" problem is real. I've been running Claude Code for side projects and the context switching cost is higher than people admit — you context-load the codebase, fire off a task, then either stare at it or switch to something else and lose the mental model entirely.

The cron-like scheduling piece is what I want to understand better. If I schedule a refactor agent to run at 2am, what happens when it hits a decision that needs human judgment — does it pause and queue, or does it guess and commit? The difference between "runs in background" and "runs unattended" is huge for trust.

Also curious about the subagent orchestration — when one agent spawns three parallel workers, how does the parent agent reconcile conflicting outputs? Is it another LLM pass, or is there a deterministic merge strategy?

Scheduled background tasks is the part I'd actually use. Quick question though, what happens when an agent task runs longer than the context window? Does the subagent remember where it left off between runs or start fresh each time? That's the wall I keep hitting building with agents lately.

I’ve used Antigravity IDE for hackathons and projects—I like how it turns prompts into structured, step-by-step tasks. Excited to see how the multi-agent feature in 2.0 improves multitasking.

I am still not getting the point of removing the whole IDE, are we finally accepting that we no more need to write a code or even see it.

Scheduled agent work gets interesting the moment a team comes back later and has to decide whether a run is safe to accept or needs review. I would want every scheduled task to leave a small receipt: owner, allowed capability set, files or services touched, stop reason, and whether it completed, paused, or hit a guardrail. Without that, background autonomy can create more context debt than leverage.

Most software abstractions succeed when they hide complexity. Multi-agent systems seem to be doing the opposite, exposing planning, delegation, coordination, and supervision as first-class concepts.

Do you think the future interface is actually a visible org chart of agents, or does that disappear entirely once the system becomes reliable enough?

how to make this bunch of ai agents run in the background so as not to allow burn all tokens my tokens at all?

google shipping a standalone agent orchestrator separate from the IDE says a lot about where this space is heading. agents aren't a feature inside dev tools anymore they're becoming their own category

Give us back the old version, where you could work on the code, both in IDE mode and in terminal mode.

I have used Antigravity IDE Version before to make projects during hackathons, academic projects. What I like about using it, is it's way of interpreting the user's written prompts or instructions in a structured way as it's finishing a to do list one at a time. With the upgrade of 2.0, I am sure the ability of achieving multi tasking through multi agent feature would be a significant update.

Parallel agents are powerful, but the monitoring layer is what makes this actually usable. Once multiple agents work at the same time, the hard part becomes catching conflicts, knowing what changed, and deciding what needs human review.

I tried 1.0. I liked one or two things. I’m a daily user of Codex and CC and planning to add one or two more. Should Antigravity be one of them?

Never used the IDE version much either. The subagent workflow is where it gets interesting: running parallel agents without babysitting each one is the shift that makes this feel different from Cursor or Claude Code. The background scheduling is a nice touch too. Excited to see how far they push the Firebase and Android integrations.

Antigravity 2.0 is awesome! I never used the IDE anyway, so I am glad that this VS Code stuff is gone. I like the subagent stuff and the new way projects are being organized. The switch could have been smoother, but I do like it. Also: Gemini 3.5 Flash is awesome! 😎