Works with

Claude Code

Amp

v0

Zed

Devin Desktop (formerly Windsurf)

Kun

Yao

About Greptile

What it does

Greptile is an AI code review agent that reviews every pull request with knowledge of the whole repository, not just the lines that changed. The aim is to catch bugs that only appear across files. Findings arrive as ordinary pull request comments, typically within a few minutes, with suggested fixes attached.

What is inside / how it works

When you connect a repository, Greptile builds a graph of the codebase covering files, functions, classes and their dependencies. On each pull request a group of agents reviews the change in parallel and checks its impact beyond the diff. You can write review rules in plain English and point Greptile at repo-specific context, and it learns your team's standards from thumbs-up and thumbs-down reactions and from replies to its comments; the docs say it stops commenting on things you ignore after two or three weeks. A newer agent called TREX writes and runs targeted tests for a pull request in a sandbox to find missed edge cases,.

Works with

Reviews run on GitHub (cloud and Enterprise Server) and GitLab (cloud and self-managed), for any programming language. Every comment has a "Fix with your agent" button that sends the issue with file paths and line numbers to Claude Code, Codex, Conductor, Cursor or Devin. An MCP server and a Claude Code plugin let agents read and resolve its comments.

How to install or start

Sign up on the website, install the GitHub or GitLab app, select repositories and open a pull request. Enterprise customers can self-host with Docker Compose or Kubernetes.

Pricing

At the time of writing (September 2026), the free Starter plan covers one active developer with 50 review credits a month. Pro costs $30 per seat per month with 50 credits per seat, extra credits at $1 each and custom rules; Enterprise is custom-priced. A standard review uses one credit and a TREX review three. Qualified non-commercial open-source projects can apply for free use, and pre-Series A startups can apply for 50% off.

Who should use it

Teams on GitHub or GitLab working in large codebases where cross-file mistakes are costly. Bitbucket and Azure DevOps are not listed, and heavy review volumes need extra credits.

code review