antigravity

🛰️ Antigravity for Claude Code

Run the Antigravity CLI (Gemini) as a collaborating sub-agent, right inside Claude Code. Claude conducts the judgement; Gemini does the heavy lifting — intelligent model routing across the SDLC.

⚡ Quick look

Claude stays the conductor; the bulk, token-heavy read ran on cheaper Gemini, and Claude verified the result.

💡 Why

you → Claude Code (conduct: design / verify / review)
         └── agy → Gemini (execute: implement / test / search)

Generation is solved; verification, judgement, and direction are the craft.

✨ What it does

• Routes work across the SDLC — Claude keeps the judgement calls; Antigravity handles scaffolding, test generation, first-pass review, and migrations under a shared AGENTS.md.
• Adds tools Claude lacks natively — live Google/web search, Vertex AI Search over your internal data, deep research, Cloud Logging. Claude reviews and re-checks the results.
• Hears audio, watches video — /antigravity:media delegates the perception to Gemini (natively multimodal, no local ffmpeg/Whisper stack): you get a timestamped digest while the full transcript is written to a file, so a 1-hour recording never lands in Claude's context.
• Cross-model verification — an independent, different-model opinion on your code.
• Background jobs — fire a long delegation, keep working, collect later.
• Internal fan-out — one delegation, and agy spawns its own subagents on the cheap side (dynamic define_subagent on agy ≥ 1.0.16; TypeName "self" + Role on any version); each leaves a readable trajectory you audit with agy-trace.
• Hand-off mode — /antigravity:handoff gives agy a whole, test-covered task; Claude reads nothing and verifies only by running the tests. The one delegation shape that measured cheaper than Claude Code alone on implementation work (0.58× per passing task; 0.43× on large tasks — and a loss on small ones), at the price of a 3–4× longer wall-clock and code that needs the human review a first draft gets.
• Built-in cost discipline — measured, not guessed (see below).
• Drops in with the discipline on — a SessionStart hook injects the cost-aware routing policy automatically (toggle in plugin settings), and the antigravity-delegate subagent does file writing on Gemini, so Claude spends no tokens generating file contents.
• No slash command required — the delegate subagent is picked up proactively for bulk work, and a prompt-level nudge flags bulk-looking requests as delegation candidates. Both are advisory: the break-even judgment stays with Claude (full auto-routing is a measured net loss below the break-even), and the nudge is toggleable (delegation_nudge).

📊 Measured results

On a large ADK multi-agent build (+ adk eval), same task / same model, 3 ways:

→ −27% vs solo@high, −64% vs solo@max, at equal quality — and the cheap Gemini work isn't even counted. Savings scale with task size; tiny one-off tasks are cheaper to just run on Claude. Full A/B: docs/AB-RESULTS.md.

Note on cost figures: numbers are estimates — token counts are approximated and rates live in prices.json. Set your real Vertex rates there before quoting any figure.

Hand-off mode, measured on real pull requests (2026-09, on agy 1.2.2 only; #91). Eight merged PRs from caddy, cli/cli, k6 and zoekt (52–2,242 lines), replayed with the PR's tests restored before scoring, Claude Opus 5 conducting, agy on Gemini 3.8 Flash, n = 2 per cell, blinded two-family review. Delegating file by file while Claude reads and specifies cost 1.33–1.68× a solo run per passing task. Handing the whole task to agy and verifying only by running the tests (agy-handoff) cost 0.58× (95% CI 0.39–0.96) at the pre-registered price deck — 0.43× on large tasks, 1.20× on small ones — with 16/16 tests passed and the Claude side alone at 0.16×; the blinded Claude judge rated that code 0.6 of 5 below the solo run (dead code, duplicated helpers), about 0.2 below the human-merged PR. At the Gemini unit price this project was actually billed (2× the promotional rate) the overall saving disappears and large tasks keep 0.77×. Full protocol, per-run records and deviations: PR #91.

🚀 Install

In Claude Code:

/plugin marketplace add yuting0624/antigravity-for-claude-code
/plugin install antigravity@antigravity-for-claude-code
/antigravity:setup        # verifies agy is installed + authenticated

Prerequisites: the Antigravity CLI (agy) installed & authenticated (agy models lists Gemini models), and Claude Code. For the same-bill cost benefit, run Claude Code on Vertex too.

Platform support: macOS, Linux, and WSL are the supported targets for headless delegation. Native Windows (Git Bash/MSYS) is not recommended — agy -p can hang with a 0-byte log when run without a real console (ConPTY); see issue #6. The wrapper now bounds this with a wall-clock guard (GNU timeout/gtimeout, returning a clean TIMEOUT instead of hanging), and doctor distinguishes a hang from an auth failure — but for reliable headless use, run from WSL/macOS/Linux.

🧩 Slash commands

The plugin's commands show up natively in Claude Code's / menu.

Background jobs are for interactive sessions (fire-and-collect). In headless claude -p (one-shot), delegate synchronously — there's no later turn to collect a result.

📦 Bringing your Claude Code setup across

/antigravity:migrate moves an existing Claude Code configuration onto agy. Dry-run by default; --apply backs up first and --uninstall --apply reverses it. Your ~/.claude is never written to.

/antigravity:migrate                             # see the plan
/antigravity:migrate --apply                     # global assets
/antigravity:migrate --apply --include-repos     # also AGENTS.md + per-repo memory

Two things are deliberately not automatic. Permissions widen when translated — Claude's allow-list holds whole command lines, while agy's command() matches a prefix — so the result is written out for review and merged only with --apply-permissions. model / effortLevel / env are reported and never written, because no honest mapping exists.

Worth knowing if you would rather do it by hand: an Antigravity rule without trigger: always_on in its frontmatter is ignored with no error and no warning, workspace .agents/ is ignored entirely unless the session is bound to an agy project, and agy plugin import claude finds nothing on a current Claude Code because it only looks one directory deep. docs/MIGRATION.md has the full layout reference, the compatibility matrix, and how each of these was measured.

🗳️ The same two models, arranged differently

This plugin is one shape of Claude and Gemini working together: conductor and executor — judgement on one side, throughput on the other, one workflow. It is also the shape for people who live in a terminal.