A GitHub code review bot that uses ChatGPT-style LLMs to comment on pull request diffs, run as a GitHub App, Action, or self-hosted Probot app.
truongnh1992/gemini-ai-code-reviewer
A GitHub Action that posts AI-generated code review comments on pull requests, triggered by a /gemini-review comment, using Google's Gemini API.
- Stars
- 258
- Forks
- 57
- Open issues
- 13
- Last commit
- 22 days ago
What is it?
Gemini AI Code Reviewer is a GitHub Action that reviews pull requests with Google's Gemini models. It collects the code changes in a pull request, filters out files you choose to skip, sends the modified code in chunks to Gemini, and adds the resulting review comments directly to the PR.
The action is set up in a workflow file in your repository and needs a Gemini API key stored as a GitHub Secret. The review runs when someone comments /gemini-review on a pull request. You can choose the Gemini model with the GEMINI_MODEL input and exclude file patterns such as *.md or lock files with the EXCLUDE input.
The project is MIT licensed and is written in Python.
Key features
- 01Triggers a review when /gemini-review is commented on a pull request
- 02Sends PR code changes to the Gemini API in chunks
- 03Lets you exclude file patterns from review
- 04Lets you choose the Gemini model through a workflow input
- 05Posts review comments directly on the pull request
Use cases
- Getting a first automated review pass on pull requests before human reviewers look at them
- Adding AI-assisted feedback to projects that want Gemini instead of other review tools
- Skipping docs, lock files and config files in code review by listing them in EXCLUDE
Quick start
- 1
Get a Gemini API key from Google AI Studio
- 2
Add the key as a GitHub Secret named GEMINI_API_KEY in your repository
- 3
Create .github/workflows/code-review.yml with the workflow from the README
- 4
Comment /gemini-review on a pull request to trigger a review
Things to know
- Requires a Gemini API key, which may incur usage costs.
- The README's example uses a model name (gemini-3.8-flash) that may not exist, so the model setting may need checking.
In collections
Topics
FAQ
- What is gemini-ai-code-reviewer?
- A GitHub Action that posts AI-generated code review comments on pull requests, triggered by a /gemini-review comment, using Google's Gemini API. Gemini AI Code Reviewer is a GitHub Action that reviews pull requests with Google's Gemini models. It collects the code changes in a pull request, filters out files you choose to skip, sends the modified code in chunks to Gemini, and adds the resulting review comments directly to the PR.
- Is gemini-ai-code-reviewer free to use? What license does it have?
- gemini-ai-code-reviewer is open source under the MIT license. Check the license terms before using it in commercial products.
- Is gemini-ai-code-reviewer still maintained?
- Actively maintained. The last commit to gemini-ai-code-reviewer was on Oct 16, 2026.
- What can I use gemini-ai-code-reviewer for?
- Getting a first automated review pass on pull requests before human reviewers look at them Adding AI-assisted feedback to projects that want Gemini instead of other review tools Skipping docs, lock files and config files in code review by listing them in EXCLUDE
- How do I install gemini-ai-code-reviewer?
- Get a Gemini API key from Google AI Studio Add the key as a GitHub Secret named GEMINI_API_KEY in your repository Create .github/workflows/code-review.yml with the workflow from the README Comment /gemini-review on a pull request to trigger a review
- Where can I get gemini-ai-code-reviewer?
- The source code and installation instructions are on GitHub: https://github.com/truongnh1992/gemini-ai-code-reviewer
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A web app and GitHub Action that group pull request changes by scope and summarize them so you can review one part at a time.
Open-source AI agent that automatically reviews pull requests and offers /describe, /review, /improve and /ask commands on GitHub, GitLab, Bitbucket and Azure DevOps.
A GitHub Action that reviews pull request diffs with an LLM and posts a small set of prioritized inline comments.
Draws each pull request as animated architecture and data-flow diagrams, posted as a comment inside the PR, for GitHub, GitLab and Bitbucket.
Ruby tool that runs in CI to automate pull request review rules, such as enforcing changelogs and PR description conventions.