Skip to main content

Welcome to diffray

AI-Powered Code Review for GitHub Pull Requests

diffray automatically reviews your pull requests using artificial intelligence and posts detailed feedback directly in GitHub.

How It Works​

  1. PR opened in GitHub Automatic trigger when you create or update a pull request

  2. AI analyzes code Advanced AI reviews your changes (5-10 minutes)

  3. Review published Detailed feedback posted as a comment in your PR

Specialized Review Agents​

diffray uses a team of specialized AI agents, each expert in their domain:

AgentWhat It Catches
🔒 Security ExpertVulnerabilities, injection attacks, exposed secrets, OWASP Top 10
⚡ Performance SpecialistN+1 queries, memory leaks, bottlenecks, scalability issues
🐛 Bug HunterNull errors, race conditions, edge cases, logic bugs
✨ Quality GuardianCode smells, dead code, unclear logic, missing validation
🏗️ Architecture AdvisorSOLID violations, tight coupling, design pattern issues
🔄 Consistency CheckerDuplicated code, pattern deviations, naming inconsistencies
📝 Documentation ReviewerOutdated docs, missing API docs, misleading comments
🧪 Test AnalystMissing coverage, flaky tests, poor isolation
🔧 General ReviewerProject conventions, git hygiene, cross-cutting concerns
🔍 SEO ExpertMeta tags, OpenGraph, structured data, search visibility
🔨 Refactoring AdvisorCode smells, SOLID violations, technical debt, complexity

diffray comes with 1,300+ built-in rules covering security, performance, bugs, compliance, and more across 49 categories including languages, frameworks, and standards. Rules are automatically applied based on what files changed in your PR — TypeScript changes get TypeScript rules, Python gets Python rules, and so on.

Compliance coverage: SOC 2, HIPAA, GDPR, LGPD, PCI-DSS rules included out of the box.

See all supported technologies →

Smart & Adaptive​

  • Context-aware — only relevant rules run based on changed files
  • Noise-free — intelligent deduplication removes repetitive findings
  • High-confidence — validation pass filters out uncertain issues
  • Codebase-aware — analyzes how changes affect existing code

Customizable​

Add project-specific rules to enforce your team's standards:

# .diffray/rules/team-standards.yaml
rules:
  - id: use_internal_logger
    agent: quality
    title: "Use internal logger"
    match:
      file_glob: ["src/**/*.ts"]
    ...

Key Features​

🤖 AI Code Review​

Get intelligent code reviews from advanced AI models that understand your codebase

⚡ Fast & Efficient​

Automatic review triggers on PR open, update, or on-demand via labels

🎯 Automatic Triggers​

Reviews start automatically when:

  • Opening a new PR
  • Pushing new commits to PR
  • Reopening a PR
  • Adding the diffray-review label

📊 Status Labels​

Track review progress through automatic labels:

  • diffray-review-started - review started
  • diffray-review-completed - review completed
  • diffray-review-failed - review failed

🔐 Secure Integration​

GitHub App with controlled permissions - you choose which repositories to grant access

What You Need​

  • A GitHub account
  • A repository where you want AI code reviews
  • Admin rights to install GitHub App
  • 5 minutes to set up

Quick Start​

  1. Sign In with your GitHub account
  2. Install GitHub App on your account/organization
  3. Add Repositories in the dashboard
  4. Create a PR and watch the magic! ✨

What's Next?​

🚀 Getting Started

Set up diffray in 5 minutes

Start here →

📖 Usage

Learn how to work with reviews

Learn more →

🧠 AI Engines

Learn about our AI technology

Discover →

🤖 Review Agents

Meet your AI review team

Explore agents →

⚙️ Custom Rules

Add your team's standards

Learn more →

📐 Writing Rules

Best practices for effective rules

Read guide →

Ready to improve your code review process? Let's get started!