Hey everyone in the Google AI & Antigravity community! ![]()
Iโm thrilled to share an open-source project that was conceived, engineered, tested, and published 100% from within Google Antigravity itself:
Antigravity Operator (agyo)
GitHub: GitHub - tiagovilasboas/antigravity-operator: The Autonomous Session Agent Engine & Outer Harness for Google Antigravity & Google AI Pro ยท GitHub
Release: v0.2.0
Why Antigravity Operator?
Google Antigravity provides incredible atomic power: bash execution, surgical file edits, subagents, and Model Context Protocol (MCP) integrations.
However, out of the box, building complex, autonomous, long-running workflows reveals a missing layer: Session State Governance & OS Lifecycle Supervision.
Without a persistent harness, agents face:
- Operational Amnesia: Decisions and progress are lost across context compactions or session restarts.
- Browser Protocol Friction: Running browser tools manually often collides with existing Chrome instances or exposes personal profiles.
- The macOS vs Linux Gap: Agents navigating headless Linux servers / VPS without
$DISPLAYcrash unless strict server flags (--headless=new,--no-sandbox,--disable-dev-shm-usage) are carefully orchestrated.
What agyo Delivers
Written in pure Go with zero external dependencies (CGO_ENABLED=0, ~6MB single static binary), agyo implements the canonical Outer Harness (Martin Fowler) model:
Deterministic Session Memory (.agents/session/): Persistsstate.md,decisions.md, andtodo.mddirectly on the filesystem so agents can pick up exactly where they left off.
Zero-Pollution Chrome Supervisor: Automatically launches and tracks an isolated Chrome instance on port 9222 (~/.gemini/antigravity-browser-profile) with graceful PID tracking and shutdown.
Display Server Auto-Detection: Seamlessly detects whether a GUI is available or switches to headless mode on Linux VPS/Docker.
Privacy & LGPD/GDPR by Design: 100% local-first, zero telemetry, full user data sovereignty.
Universal One-Line Installer & Homebrew: Instant installation on macOS and Linux.
Quick Start
raw.githubusercontent