Building an agentic PR reviewer with Antigravity SDK

Google is transitioning Gemini CLI into Antigravity CLI, a new agent-first platform for complex multi-agent workflows. A developer built an automated pull request reviewer using the Antigravity SDK and a composite GitHub Action to offload first-pass code review, reducing cognitive overload for human reviewers. The agentic pipeline runs on PR open/reopen events and can be triggered manually via comments, using separate context and system instructions to catch bugs that the original AI code generator might miss.

As announced in this blog post https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/?utm campaign=CDR 0x87fa8d40 default b517845989&utm medium=external&utm source=blog on June 18, 2026, Gemini CLI and Gemini Code Assist IDE extensions will stop serving requests for Google AI Pro and Ultra, as well as those using it free of charge using Gemini Code Assist for individuals. Google is unifying its AI terminal tools by transitioning the community-focused Gemini CLI into Antigravity CLI, a new agent-first platform built for complex, multi-agent workflows. With this transition timeline in place, development teams relying on Gemini CLI for repository management and automated tasks must establish a migration path. In this post, I will show you how to transition seamlessly by building an automated "first-pass" pull request reviewer using the Google Antigravity SDK https://antigravity.google/product/antigravity-sdk?utm campaign=CDR 0x87fa8d40 default b517845989&utm medium=external&utm source=blog and the run-agy-sdk https://github.com/rsamborski/run-agy-sdk composite GitHub Action https://github.com/features/actions . The approach I am proposing also solves another pressing issue for modern engineering teams: cognitive overload. As Addy Osmani https://x.com/addyosmani recently pointed out, there is an orchestration tax https://x.com/addyosmani/status/2059844244907696186 to using AI for coding. The time developers save generating code is often pushed onto reviewers as large, complex PRs, causing context switching and cognitive fatigue. By offloading the tedious "first pass" search to an Antigravity agent, human reviewers can mitigate this tax and focus on high-level architecture and safeguarding quality. AI-generated code can be deceptively good. It is often clean, well-documented, and syntactically correct. This makes it harder for human reviewers to spot subtle logical bugs or security vulnerabilities that might not be immediately obvious. In a large codebase, manually verifying every change is simply not feasible. This is why we need autonomous agents that can step into the codebase and analyze it from a fresh perspective. But if a developer used an LLM to generate the code, how can we trust another AI to find the bugs? The answer lies in the agent architecture and context separation. Developers might write code using any tool — whether it's CLI, an IDE extension, or various models like Gemini 3.5 Flash or Gemini 3.1 Pro. The reviewer, however, is a managed Antigravity Agent running via a separate SDK integration. This agent has a specialized, low-freedom persona and strict system instructions that force it to act as an adversarial code auditor rather than a developer. Furthermore, it operates in an isolated environment. Because it has a different system prompt, safety guardrails, and context boundaries, the agent reviews the changes with a completely fresh perspective, catching logical bugs and vulnerabilities that the original generator might miss. To demonstrate it in practice I created an agentic review pipeline, which: synchronize trigger in pull request workflows to prevent redundant review runs and endless loops. Instead, runs reviews on opened and reopened events, and triggers subsequent passes manually by posting a @agy /review comment on the PR.You can find the code at run-agy-sdk https://github.com/rsamborski/run-agy-sdk . The run-agy-sdk https://github.com/rsamborski/run-agy-sdk is a composite GitHub Action that runs the Google Antigravity SDK google-antigravity directly on the GitHub Actions host runner. By running directly on the host, the Antigravity SDK has access to the host's Docker daemon. This allows the SDK to spawn Docker-based MCP servers like the GitHub MCP server to read files, run tests, and post reviews. Sub-containers should ideally run with restricted network access and read-only filesystems where possible to prevent an LLM from being tricked into executing arbitrary destructive commands. The limited set of permissions is handled in the GitHub Action configuration see here https://github.com/rsamborski/run-agy-sdk/blob/da0ff77fc9dfc82e5ad89a430bc51476aeb8f867/.github/workflows/antigravity-autonomous-review.yml L33 . Whereas the Antigravity agent has a limited number of tools it can use from GitHub MCP see here https://github.com/rsamborski/run-agy-sdk/blob/da0ff77fc9dfc82e5ad89a430bc51476aeb8f867/run agent.py L160-L161 . Moreover the workflow is explicitly protected from running automatically on forks, preventing unauthorized code execution. The automated review job will only run if the pull request originates from the same repository see here https://github.com/rsamborski/run-agy-sdk/blob/da0ff77fc9dfc82e5ad89a430bc51476aeb8f867/.github/workflows/antigravity-autonomous-review.yml L45 . On-demand reviews triggered by commenting @agy /review are restricted so that they can only be initiated by maintainers see here https://github.com/rsamborski/run-agy-sdk/blob/da0ff77fc9dfc82e5ad89a430bc51476aeb8f867/.github/workflows/antigravity-autonomous-review.yml L59-L61 . The demo below shows the action triggered by a new PR: Let's walk through the setup process step-by-step. The action requires a Google Gemini or Antigravity API key to authenticate language model interactions. ANTIGRAVITY API KEY and paste your API key as the value.Add a new file in your repository at .github/workflows/antigravity-review.yml and add the following configuration: name: '🔎 Antigravity PR Review' on: pull request: types: opened, reopened workflow dispatch: concurrency: group: '${{ github.workflow }}-${{ github.event.pull request.number || github.ref name }}' cancel-in-progress: true jobs: antigravity-review: runs-on: 'ubuntu-latest' timeout-minutes: 20 permissions: contents: 'read' pull-requests: 'write' issues: 'write' steps: - name: 'Checkout Repository' uses: 'actions/checkout@v6' with: persist-credentials: false - name: 'Run Antigravity PR Review' uses: 'rsamborski/run-agy-sdk@main' id: 'agy pr review' with: api-key: '${{ secrets.ANTIGRAVITY API KEY }}' github-token: '${{ secrets.GITHUB TOKEN }}' mode: 'review' prompt: '/antigravity-review' trust-workspace: 'true' sandbox-profile: 'true' Pro Tip: Pin the action version to a specific commit SHA e.g., rsamborski/run-agy-sdk@<commit-sha rather than using @main . This prevents unexpected breaks from upstream updates. While you can reference run-agy-sdk directly in your workflows, its real power lies in using it as a blueprint. I encourage you to fork the repository https://github.com/rsamborski/run-agy-sdk and use it as a template to build your own custom, agentic GitHub Actions. By modifying the safety policies, custom tools, or prompts in run agent.py , you can tailor the agent's review behavior to your team's specific codebase, style guidelines, and compliance rules. For a full workflow template supporting both automated PR reviews and comment-triggered reviews, refer to the workflows https://github.com/rsamborski/run-agy-sdk/blob/main/.github/workflows folder in the repository. Automating code reviews is a necessity as AI-generated code volumes increase. By using run-agy-sdk , you can run the Antigravity SDK to review PRs automatically and shift more of the burden of code quality assurance away from human reviewers. This project was inspired by the run-gemini-cli https://github.com/google-github-actions/run-gemini-cli action, while shifting to the recently released Antigravity SDK. It is a personal sample implementation of how to run the Antigravity SDK in a GitHub Action, and is not an officially supported Google product. I’d love to hear how you’re using Antigravity for your agentic workflows. Are you building automated code review loops or keeping a tighter leash on your agents?