Presubmit - AI Code Reviewer

Context-aware, intelligent and instant PR reviews

     

Optimize your code review process with Presubmit's AI Code Reviewer that catches bugs, suggests improvements, and provides meaningful summary - all before human reviewers take their first look.

• 🔍 Instant, In-depth PR Analysis: Catches bugs, security issues, and optimization opportunities in real-time
• 🎯 Focus on What Matters: Let AI handle the basics while humans focus on architecture and complex logic
• ✨ Title and description generation: Save time by having the AI generate meaningful title and description for your PR
• 💬 Interactive & Smart: Responds to questions and generates code suggestions right in your PR
• ⚡ Lightning-Fast Setup: Up and running in 2 minutes with GitHub Actions

🤝 Note: Presubmit is designed to complement human reviewers, not replace them. It helps catch security issues and bugs early on while also providing context about the overall change, making the human review process more efficient.

See it in Action

💡 View full example PR review

Automated analysis detects potential issues and provides actionable insights:

Interactive discussions help clarify implementation details:

Usage

Step 1: Add LLM_API_KEY secret

1. Go to your repository's Settings > Secrets and Variables > Actions
2. Click "New repository secret"
3. Add a new secret with:
   • Name: LLM_API_KEY
   • Value: Your API key from one of these providers:
     • Anthropic Console (Claude)
     • OpenAI API (GPT-4)
     • Google AI Studio (Gemini)

Step 2: Create GitHub Workflow

Add this GitHub Action to your repository by creating .github/workflows/presubmit.yml:

name: Presubmit.ai

permissions:
  contents: read
  pull-requests: write
  issues: write

on:
  pull_request_target:
    types: [opened, synchronize]
  pull_request_review_comment:
    types: [created]

jobs:
  review:
    runs-on: ubuntu-latest
    steps:
      - name: Check required secrets
        run: |
          if [ -z "${{ secrets.LLM_API_KEY }}" ]; then
            echo "Error: LLM_API_KEY secret is not configured"
            exit 1
          fi
      - uses: presubmit/ai-reviewer@latest
        env:
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
          LLM_MODEL: "claude-3-5-sonnet-20241022"

The action requires:

• GITHUB_TOKEN: Automatically provided by GitHub Actions
• LLM_API_KEY: Your API key (added in step 1)
• LLM_MODEL: Which LLM model to use. Make sure the model is supported and matches the LLM_API_KEY.

GitHub Enterprise Server Support

If you're using GitHub Enterprise Server, you can configure the action to work with your instance by adding these environment variables:

      - uses: presubmit/ai-reviewer@latest
        env:
          GITHUB_API_URL: "https://github.example.com/api/v3"
          GITHUB_SERVER_URL: "https://github.example.com"

You can also configure these settings using input parameters:

      - uses: presubmit/ai-reviewer@latest
        with:
          github_api_url: "https://github.example.com/api/v3"
          github_server_url: "https://github.example.com"

Make sure to replace https://github.example.com with your actual GitHub Enterprise Server URL.

Features

🤖 Smart Reviews

• In-depth Analysis: Line-by-line review with context-aware suggestions
• Auto PR Summary: Concise, meaningful summaries of changes
• Code Quality: Catches bugs, anti-patterns, and style issues
• Interactive: Responds to questions and clarifications in comments

🛡️ Security & Quality

• Vulnerability Detection: Catches security issues and leaked secrets
• Best Practices: Enforces coding standards and security guidelines
• Performance: Identifies potential bottlenecks and optimizations
• Documentation: Ensures proper code documentation and clarity

⚙️ Configurable

• Mention @presubmit in PR title for auto-generation
• Disable reviews with @presubmit ignore comment
• Configurable review depth and focus areas
• Customizable rules and preferences

⚡ Seamless Integration

• 2-minute setup with GitHub Actions
• Works with all major LLM providers (Claude, GPT-4, Gemini)
• Instant feedback on every PR
• Zero maintenance required

Local CLI (Dry-Run) Testing

Run the reviewer locally against real PRs using your GitHub authentication.

Prerequisites

• Node.js 18+
• GitHub CLI authenticated: gh auth login
• .env file at repo root with:
  • LLM_API_KEY=... (your API key)
  • LLM_MODEL=... (e.g., claude-3-5-sonnet-20241022, gpt-4o-mini)
  • Optional: LLM_PROVIDER=ai-sdk (default)

Build

pnpm install
pnpm build

Commands

List PRs:

pnpm review -- --list-prs --state open --limit 5

Review a PR (dry-run):

pnpm review -- --pr 123 --dry-run

Save output to file:

# Auto-generates filename: dry/pr-123.txt
pnpm review -- --pr 123 --dry-run --out

# Custom output path
pnpm review -- --pr 123 --dry-run --out my-review.txt

Specify repository:

pnpm review -- --pr 123 --owner myorg --repo myrepo --dry-run

Or set in .env:

GITHUB_REPOSITORY=myorg/myrepo

Notes

• Uses your gh auth token automatically
• --dry-run mode skips all GitHub API writes and logs what would be posted
• Without --dry-run, the review will be posted to GitHub
• Defaults to repository from GITHUB_REPOSITORY env var or presubmit/ai-reviewer

Show Your Support! ⭐

If you find Presubmit helpful in improving the review process:

• Star this repository to show your support and help others discover it
• Share your experience by creating a GitHub Issue
• Follow me on X/Twitter for updates
• Consider contributing to make it even better