ThinkReview

An AI copilot for GitLab and azure devops that automates code reviews with smart suggestions, multi-language support, and proactive insights to improve your merge request workflow.

Comment

🧠 ThinkReview — AI Code Review Co-Pilot for GitLab & Azure DevOps

🚀 Inspiration

Code reviews were the biggest bottleneck in my development workflow — slow, repetitive, and often missing subtle bugs.
Existing AI tools were too complex, requiring heavy CI/CD integrations just to get started.

I wanted to build a true AI “co-pilot” that assists human reviewers rather than replacing them — with a focus on ease of use and interactive collaboration.

💡 What It Does

ThinkReview is an AI-powered code review assistant for GitLab and Azure DevOps, delivered as a zero-setup Chrome extension.

It:

  • 🔍 Automatically analyzes code diffs for bugs, security vulnerabilities, and best-practice violations
  • 🧾 Generates a concise summary and detailed analysis of every code change
  • 💬 Suggests Smart Follow-Up Questions (see Image 1) to turn static reviews into interactive learning sessions
  • ⚙️ Works seamlessly on both cloud and self-hosted GitLab & Azure DevOps instances

🛠️ How I Built It

  • Frontend: Chrome Extension for frictionless, zero-setup UX
  • Backend: Powered by Google Gemini 2.5 Pro API for real-time code analysis
  • Architecture: Security-first — code diffs are processed in real time and never stored
  • Security:
    • All traffic via HTTPS
    • Authentication through Google OAuth
    • No persistent code or data storage

⚔️ Challenges I Ran Into

The biggest challenge was the “silent user” problem — high usage (300+ reviews from some users) but no responses to emails or upgrade prompts.

I discovered the free plan was too generous (15+ reviews/day), removing incentive to upgrade.
This taught me the importance of designing freemium tiers that create demand, not just serve free users indefinitely.

🏆 Accomplishments I’m Proud Of

  • ✅ Achieved a true zero-setup experience, loved by developers
  • 🌱 Gained organic adoption from teams at lastminute.com, vidio.com, and hepsiburada.com
  • 🔄 Expanded from GitLab → Azure DevOps purely through user demand
  • 🤖 Built the innovative “Smart Follow-Up Questions” feature that transforms AI into a teaching partner

📚 What I Learned

  • 🎯 Freemium balance: A free plan must clearly motivate upgrades
  • 💡 Solve one pain point well: Speeding up painful code reviews created instant traction
  • 🧩 Augment, don’t replace: The best dev tools enhance human judgment, not replace it
  • 🔐 Trust is everything: Transparency and strong security are non-negotiable for developer adoption

🔮 What’s Next for ThinkReview

  • 💼 Pro & Team Tiers — advanced security scanning, usage analytics, higher limits
  • 👥 Team Features — centralized billing, management dashboards, custom review rules
  • 🌍 Open Source Launch — invite the developer community to contribute, extend integrations, and build transparency into the core
  • 🔁 Feedback Loop — thumbs up/down to train a learning AI and reduce false positives

Built with ❤️ to make code reviews faster, smarter, and more human.

Built With

Share this project:

Updates

posted an update —

Hey everyone

A few months ago I started building a small side project to make code reviews a little less painful. Today I’m excited to share two big updates:

ThinkReview is now open source

ThinkReview now supports Ollama (run local LLMs for private code reviews!)

If you haven’t heard of ThinkReview before, here’s the quick intro.

What is ThinkReview?

ThinkReview is a browser extension that helps you review code directly inside your GitLab/GitHub/Bitbucket merge requests.

You can literally chat with your MR, ask questions about the diff, explore potential bugs, and generate review comments.

The key difference from typical AI review bots (CodeRabbit, CodeAnt, etc.) is:

It does not spam your PR with automatic comments

It gives you a private AI assistant inside the MR UI

You stay fully in control of the final review. Think of it as “AI-assisted thinking,” not automated reviewing.

This is especially useful for devs who still prefer reviewing code in the browser, not inside an IDE or via CI bots.

Update #1: ThinkReview is now Open Source

You can explore the code, file issues, request features, or contribute.

GitHub Repo: https://github.com/Thinkode/thinkreview-browser-extension

Making the project open source was the #1 request from early users, especially those in companies with strict audit/security requirements.

Update #2: Ollama Support (Run Local LLMs)

As of version 1.4.0, ThinkReview can now connect to Ollama, letting you run:

  • Qwen Coder
  • Llama 3
  • DeepSeek
  • Codestral
  • Any model supported by Ollama

Why this is awesome:

  • 100% local → your code never leaves your machine
  • Free
  • Works great with self-hosted GitLab
  • No API keys required

For privacy-focused teams (or anyone who prefers local inference), this is a huge upgrade.

Installation

ThinkReview works on all Chromium browsers.

Chrome Web Store: https://chromewebstore.google.com/detail/thinkreview-ai-code-revie/bpgkhgbchmlmpjjpmlaiejhnnbkdjdjn

Join the Discussion

If you have ideas, want to contribute, or need help setting up local models, feel free to reach out:

I’d love to hear feedback from this community — especially from developers experimenting with LLM-assisted workflows.

Thanks for reading! — Jay

Log in or sign up for Devpost to join the conversation.