ThinkReview - Agentic code reviews in your Pull Requests sidebar

by
Relaunched after 9 months, ThinkReview is now an agentic AI code review sidebar for GitHub, GitLab, Azure DevOps, and Bitbucket, including self-hosted versions. It adds full-repo context, custom review agents, summaries, bug/security checks, chat, and missing-test suggestions without CI setup, webhooks, bot accounts, or automatic PR comment spam.

Add a comment

Replies

Best
Maker
📌
Hey Product Hunt, We first launched ThinkReview here around 9 months ago as a simple AI code review extension for GitLab merge requests. At the time, it only reviewed the diff, only supported GitLab, only used Gemini models, and had no custom review agents. Since then, we rebuilt it into a much broader PR review workspace. ThinkReview now adds agentic AI code review directly inside your GitHub, GitLab, Azure DevOps, and Bitbucket PR/MR sidebar. It supports both cloud and self-hosted versions of those platforms, can use full-repo context instead of only isolated diff hunks, and keeps AI review in a private sidebar instead of automatically posting bot comments into the PR. What’s new since the first launch: Full-repo context, not just the diff Custom review agents for security, performance, API compatibility, accessibility, and team-specific checks Multi-platform support: GitHub, GitLab, Azure DevOps, and Bitbucket Self-hosted support for GitHub Enterprise, self-managed GitLab, Azure DevOps Server, and Bitbucket Data Center/Server More model options: cloud models, OpenRouter, and local Ollama No automatic PR comment spam: reviewers decide what gets posted Zero setup: no CI config, webhooks, or bot accounts I built ThinkReview this way because AI code review is most useful when it helps the reviewer think, not when it floods the PR with comments the team still has to triage. The agent system is the biggest change. You can create specialized reviewers with their own instructions and references, then run them in separate sidebar tabs alongside the main review. Would love feedback from developers and teams who review a lot of code: Do you prefer AI review as automatic PR comments, or as a private sidebar first where the human reviewer stays in control?
💎 Pixel perfection

Came in expecting yet another noisy review bot, but the sidebar-only approach actually respects the workflow. Liked that I could point it at a local Ollama model and skip sending code anywhere, that part feels ahead of its time.

 very pleased to hear this feedback , please reach out to thinkreview.dev and happy to chat further and get you on free trial

💡 Bright idea

Love that the reviewer stays in control of what actually gets posted to the PR, it's a thoughtful answer to the usual AI review tool fatigue.

 Thank you Buglem , if you created an account clready please reach out at and Im happy to get you on a trial if you are interested

Hey Product Hunt! We just shipped ThinkReview v2.3.6, focusing heavily on developer experience and UI polish. We replaced annoying browser pop-ups with slick toasts, made severity layout the default, and added an interactive tour for first-time users. Check out the full release notes here: