AI Review

AI-powered code review tool.

Made with ❤️ by @NikitaFilonov

❤️ Support AI Review

If AI Review helps you reduce noise in pull requests and saves time in code reviews, consider supporting its development.

Your support helps to:

• improve review accuracy and reduce false positives
• expand integrations (GitHub, GitLab, Azure DevOps, etc.)
• develop new features and maintain the project

👉 https://boosty.to/ai_review

📑 Table of Contents

• ✨ About
• 🧪 Live Preview
• 🚀 Quick Start
• ⚙️ ️CI/CD Integration
  • 🚀 GitHub Actions
  • 🚀 GitLab CI/CD
• 📘 Documentation
• ⚠️ Privacy & Responsibility Notice

✨ About

AI Review is a developer tool that brings AI-powered code review directly into your workflow. It helps teams improve code quality, enforce consistency, and speed up the review process.

✨ Key features:

• Multiple LLM providers — choose between OpenAI, Claude, Gemini, Ollama, Bedrock, OpenRouter, or Azure OpenAI and switch anytime.
• VCS integration — works out of the box with GitLab, GitHub, Bitbucket Cloud, Bitbucket Server, Azure DevOps, and Gitea.
• Customizable prompts — adapt inline, context, and summary reviews to match your team’s coding guidelines.
• Agent mode — iterative ReAct-style loop where the model can explore the repository with shell commands (ls, cat, rg, git) before producing a final review, giving it deeper context than a single-shot call.
• Reply modes — AI can now participate in existing review threads, adding follow-up replies in both inline and summary discussions.
• Flexible configuration — supports YAML, JSON, and ENV, with seamless overrides in CI/CD pipelines.
• AI Review runs fully client-side — it never proxies or inspects your requests.

AI Review runs automatically in your CI/CD pipeline and posts both inline comments, summary reviews, and now AI-generated replies directly inside your merge requests. With agent mode enabled, the model can autonomously explore the codebase before reviewing, resulting in more accurate and context-aware feedback. This makes reviews faster, more conversational, and still fully under human control.

🧪 Live Preview

Curious how AI Review works in practice? Here are three real Pull Requests reviewed entirely by the tool — one per mode:

👉 Each review was generated automatically via GitHub Actions using the corresponding mode:

ai-review run-inline
ai-review run-summary
ai-review run-context
ai-review run-inline-reply
ai-review run-summary-reply

🚀 Quick Start

Install via pip:

pip install xai-review

📦 Available on PyPI

Or run directly via Docker:

docker run --rm -v $(pwd):/app nikitafilonov/ai-review:latest ai-review run-summary

🐳 Pull from DockerHub

👉 Before running, create a basic configuration file .ai-review.yaml in the root of your project:

llm:
  provider: OPENAI

  meta:
    model: gpt-4o-mini
    max_tokens: 1200
    temperature: 0.3

  http_client:
    timeout: 120
    api_url: https://api.openai.com/v1
    api_token: ${OPENAI_API_KEY}

vcs:
  provider: GITLAB

  pipeline:
    project_id: "1"
    merge_request_id: "100"

  http_client:
    timeout: 120
    api_url: https://gitlab.com
    api_token: ${GITLAB_API_TOKEN}

👉 This will:

• Run AI Review against your codebase.
• Generate inline and/or summary comments (depending on the selected mode).
• Use your chosen LLM provider (OpenAI GPT-4o-mini in this example).

Note: Running ai-review run executes the full review (inline + summary). To run only one mode, use the dedicated subcommands:

• ai-review run-inline
• ai-review run-context
• ai-review run-summary
• ai-review run-inline-reply
• ai-review run-summary-reply

AI Review can be configured via .ai-review.yaml, .ai-review.json, or .env. See ./docs/configs for complete, ready-to-use examples.

Key things you can customize:

• LLM provider — OpenAI, Gemini, Claude, Ollama, Bedrock, OpenRouter, or Azure OpenAI
• Model settings — model name, temperature, max tokens
• VCS integration — works out of the box with GitLab, GitHub, Bitbucket Cloud, Bitbucket Server, Azure DevOps, and Gitea
• Agent mode — enable iterative repository exploration before review
• Review policy — which files to include/exclude, review modes
• Prompts — inline/context/summary/agent prompt templates

👉 Minimal configuration is enough to get started. Use the full reference configs if you want fine-grained control ( timeouts, artifacts, logging, etc.).

⚙️ CI/CD Integration

AI Review works out-of-the-box with major CI providers. Use these snippets to run AI Review automatically on Pull/Merge Requests.
Each integration uses environment variables for LLM and VCS configuration.

For full configuration details (timeouts, artifacts, loggin