mberneti

mberneti / clab

Public

Open source Claude skill for automated GitLab MR reviews. Configurable lint rules, semantic analysis, and inline comment posting for self-hosted GitLab instances.

33
0
69% credibility
Found May 27, 2026 at 33 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Go
AI Summary

clab is an open-source tool that brings automated code review to GitLab merge requests. It integrates with AI coding assistants like Claude Code and Cursor, automatically scanning code changes for common issues like hardcoded secrets, commented-out code, missing ticket references in TODOs, and oversized file changes. The tool posts findings as inline comments directly on merge requests, making it easy for teams to catch problems before merging. It also includes a learning feature that analyzes past merge requests to generate project-specific review rules tailored to your codebase. The project is well-documented, uses standard GitLab APIs, and stores all credentials locally.

How It Works

1
💬 You hear about automated code review

A teammate tells you about a tool that can automatically review your GitLab merge requests using AI.

2
📦 You install the review tools

You run a simple installation command that puts four helpful programs on your computer.

3
🔐 You connect your GitLab account

You create a personal access token in GitLab settings so the tool can read your merge requests.

4
🤖 You ask for a code review

In your AI coding assistant, you type a simple command pointing to any merge request URL.

5
The tool finds issues automatically
⚡
Quick automated scan

Built-in rules catch secrets, dead code, and large file changes right away

📚
Smart AI analysis

The AI assistant then adds its own insights about code quality and best practices

6
💭 You can teach it your project's rules

Optionally, you point it at past merge requests and it learns what issues matter most for your codebase.

✅ Review comments appear on your merge request

All findings are posted as inline comments directly on your GitLab merge request, ready for discussion.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 33 to 33 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is clab?

clab is an open-source Go tool that brings AI-powered code review to GitLab merge requests through Claude Code skills. It fetches MR diffs, runs configurable lint rules, and posts findings as inline GitLab comments. You trigger reviews with simple slash commands like `/clab-review `, and it supports dry-runs, severity filtering, and rules-only modes. The tool also analyzes past MRs to automatically generate project-specific review rules.

Why is it gaining traction?

The main appeal is zero-overhead integration with Claude Code or Cursor—both natively read the same slash command format. Unlike GitHub-focused AI review tools, clab works with self-hosted GitLab instances and keeps everything local with no external services. Its built-in rules catch secrets, dead code, unlinked TODOs, and oversized diffs, while the `/clab-prepare-rules` command learns from your MR history to create custom rules. The CLI-first approach means you get composable binaries for fetching diffs, linting, posting comments, and listing MRs.

Who should use this?

Backend teams on GitLab who want consistent automated review patterns and have adopted Claude Code in their workflow. Security-conscious teams will appreciate the secrets detection and configurable rules. Small-to-medium teams without dedicated CI/CD review tooling but with Claude access will find the most value here.

Verdict

This is a clever idea that fills a real gap for GitLab users, but with only 33 stars and a credibility score of 0.7%, it's early-stage and largely untested at scale. The documentation looks solid and the Go implementation is efficient, but wait for more community validation before trusting it in production pipelines.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.