agy-bridge

Get a second opinion on Claude Code's work from a Google Antigravity (AGY) agent, and let the two of them talk it through: to review what Claude made, or to think a task through before Claude starts it.

agy-bridge is an MCP server. It gives Claude Code tools to start an AGY agent, send it work or a problem, read its answer, reply with fixes, counter-arguments or answers, and keep the conversation going over several turns, even across Claude Code sessions.

Why a second agent, and how the review should run: the review method behind agy-bridge.

Not affiliated with Google or Anthropic. agy-bridge is an independent open-source project. Antigravity and Gemini are Google products; Claude and Claude Code are Anthropic products. It drives the agy command-line tool you already have, using your own Antigravity login.

How it looks

You ask Claude Code:

Implement the retry logic from the plan, then run AGY with the code-review skill.

Claude writes the code and runs the tests. Then it starts an AGY code-reviewer, which reads the project, runs the tests itself and returns a structured review:

{
  "verdict": "changes_requested",
  "summary": "Retries work, but the backoff ignores Retry-After and one path never gives up.",
  "findings": [
    {"severity": "high", "category": "correctness", "location": "client.py:88",
     "issue": "...", "recommendation": "..."}
  ],
  "questions_for_claude": ["Should a 429 count towards max_attempts?"]
}

Claude fixes what it agrees with, argues with what it doesn't, answers the questions and sends the new diff back. AGY re-checks. When they agree, or after a few rounds, Claude reports the outcome to you, including any point they still disagree on.

It isn't only for code. Before starting something new, you might ask:

Before you draft my conference talk on agy-bridge, brainstorm it with AGY's thinking partner.

AGY's thinking-partner picks a technique (here, writing the announcement first, and a pre-mortem) and checks where Claude's claims come from before building on them:

{
  "verdict": "needs_discussion",
  "reframed_problem": "Show developers who already use Claude Code why a second, different model makes their reviews better.",
  "assumptions": [
    {"statement": "The audience knows what MCP is", "source": "inferred",
     "risk": "If they don't, the first ten minutes are lost on setup."}
  ],
  "options": [
    {"idea": "Live demo of one bug caught by AGY that Claude missed",
     "gains": "Memorable, concrete", "costs": "Demo risk; needs a reliable example"}
  ],
  "questions_for_claude": ["(user) Who is the audience: beginners or MCP users?"]
}

Claude passes your questions to you, discusses the options with AGY, and brings you a short list to choose from before writing anything.

Related MCP server: mcp-agent-review

Requirements

• AGY CLI, installed and signed in. agy-bridge finds it at ~/.gemini/bin/agy, on PATH, or at $AGY_BIN. Tested with AGY 1.5.1 and 1.5.2.

• Claude Code, with the claude command on PATH (used to register the server).

• Python 3.11+ and uv.

• macOS or Linux. Tested on macOS; Linux runs in CI. Windows is not supported.

Quick start

git clone https://github.com/kulaone/agy-bridge.git
cd agy-bridge
uv sync
uv run agy-bridge install

Restart Claude Code, then check the setup:

uv run agy-bridge doctor

install copies three AGY agents with their skills, plus a Claude skill, and registers the server:

It never overwrites a file you have changed, and agy-bridge uninstall removes only what it added. See the install guide for per-project installs and other options.

Use it

Ask Claude Code in your own words:

• "Review my uncommitted changes with AGY."

• "Run AGY with the code-review skill on this branch against main, using Argon high."

• "Ask the AGY design reviewer about docs/design/sync.md before we build it."

• "Before we start, brainstorm with AGY how to onboard new customers. Go wild."

• "Have AGY's thinking partner review the launch email draft."

• "What is AGY doing right now?"

• "Resume yesterday's AGY review of this project."

The user guide covers choosing models, long reviews, reading the results and resuming sessions.

What AGY may do

AGY is a full reviewer. It may read the whole project, run tests, linters and builds, and experiment in its own scratch folder. Its instructions forbid changing the project, and its file-writing tools only work in that scratch folder. Shell commands can't be limited that way, so agy-bridge also:

• detects any change to the project during each turn and reports it to Claude, which tells you;

• backs up your uncommitted work before each turn, so it can be restored;

• never runs AGY with --dangerously-skip-permissions.

Read SECURITY.md before using it on code you can't afford to have touched.

Use at your own risk. agy-bridge is provided as is, with no warranty and no support commitment. You are responsible for what it and AGY do on your machine.

Documentation

• The review method: why agy-bridge exists, and the four-stage review it runs

• Install guide: install options, per-project installs, uninstalling

• User guide: reviews, models, results, sessions, the tools

• Configuration: environment variables, files and folders

• Writing your own agents: add a docs or security reviewer

• Troubleshooting

• Architecture: how it works and why

• Contributing and the changelog

License

MIT © Daniel Gwerzman