# Greptile

> AI code review that checks every pull request against your full codebase context

- Category: [Coding AI](https://finderatlas.com/categories/coding-ai)
- Pricing: Freemium
- Website: https://www.greptile.com
- Platforms: Web, API
- API: available
- Made by: Greptile, founded 2023, San Francisco, CA
- Last updated: 2026-10-19
- FinderAtlas page: https://finderatlas.com/tools/greptile

## Overview

Greptile is an AI code review tool that reviews pull requests on GitHub and GitLab with context from the whole repository rather than only the changed lines. It builds a graph index of a codebase (files, functions and dependencies) and runs a set of narrowly scoped agents in parallel to flag bugs, security risks, style violations and missed edge cases, including issues that span several files. Findings are posted as comments and a summary with a confidence score on the pull request.

## Key features

- Full-Codebase Context
- Parallel Review Agents
- Custom Rules
- Learning from Comments
- Review Summaries
- Fix in Your Agent
- TREX Runtime Validation
- MCP Server and Claude Code Plugin
- Self-Hosting

## Pricing

- **Starter** ($0): Free for one active developer
- **Pro** ($30/user/mo): Teams, marked Recommended on the pricing page
- **Enterprise** (Custom): Organizations at scale

## Best for

- Automated pull request review on large codebases, enforcing team coding standards, feeding review findings to coding agents

## Who uses it

- Software Engineers
- Engineering Managers
- Engineering Teams
- Open Source Maintainers
- Security-Conscious Enterprises

## Strengths

- Reviews use a graph index of the whole repository, so findings can cover impact beyond the changed lines.
- Plain-English custom rules and learning from past pull request comments adapt reviews to team standards.
- Works with GitHub, GitLab and Bitbucket, and hands findings to Claude Code, Cursor, Codex or Devin.
- Self-hosting and air-gapped deployment are available for regulated organizations.
- Free tier for one developer, free use for qualified open source, and 50% off for early startups.

## Limitations

- Third-party comparisons report more false positives than some competitors; one competitor-run test claims nearly 60% of comments were nitpicks or false positives, which should be read as a rival's claim.
- Pro costs $30 per seat per month and extra credits cost $1 each, with Plus and Apex reviews using 3 and 10 credits.
- Self-hosting, SSO/SAML and GitHub Enterprise support require the custom-priced Enterprise plan.
- Focused on pull request review only; it is not an editor or coding assistant.

## Not recommended for

- Teams that want a purely local review tool or that have little tolerance for review comment noise

## Integrations

- GitHub
- GitLab
- Bitbucket
- Claude Code
- Cursor
- Codex
- Devin

## FinderAtlas editorial scores (out of 10)

- Ease of Use: 8.2/10
- Feature Depth: 8.4/10
- Value for Money: 7.6/10
- Performance & Speed: 7.8/10
- Documentation & Support: 8/10

## Alternatives

- [Groq](https://finderatlas.com/tools/groq): Fast, OpenAI-compatible inference API for open models, running on custom LPU chips ([compare](https://finderatlas.com/compare/greptile-vs-groq))
- [Browserbase](https://finderatlas.com/tools/browserbase): Cloud browser infrastructure and APIs that let AI agents browse and act on the web ([compare](https://finderatlas.com/compare/browserbase-vs-greptile))
- [Browser Use](https://finderatlas.com/tools/browser-use): Open-source library and cloud platform for AI agents that control real web browsers ([compare](https://finderatlas.com/compare/browser-use-vs-greptile))
- [HOL Guard](https://finderatlas.com/tools/hol-guard): Local approvals for AI coding agent actions before they touch your machine ([compare](https://finderatlas.com/compare/greptile-vs-hol-guard))
- [Macroscope](https://finderatlas.com/tools/macroscope): AI code review, agent orchestration and engineering status updates for GitHub teams ([compare](https://finderatlas.com/compare/greptile-vs-macroscope))
- [Momentic](https://finderatlas.com/tools/momentic): AI QA platform that writes, runs and maintains end-to-end tests from plain English ([compare](https://finderatlas.com/compare/greptile-vs-momentic))
- [Warp](https://finderatlas.com/tools/warp): Open-source terminal with built-in AI agents and cloud infrastructure for coding workflows ([compare](https://finderatlas.com/compare/greptile-vs-warp))
- [CodeRabbit](https://finderatlas.com/tools/coderabbit): AI code review that checks, explains and prioritizes every pull request before merge ([compare](https://finderatlas.com/compare/coderabbit-vs-greptile))

## Recent updates

- 2026-09-16: Added a confidence score, severity-sorted findings and one Fix All button using the preferred agent
- 2026-08-05: Agent v5 enabled for all users, running a swarm of narrowly scoped agents in parallel

## FAQ

**Which source control platforms does Greptile support?**

The site lists GitHub and GitLab, and the docs also list GitHub Enterprise Server and Enterprise Cloud, GitLab Self-Managed, and Bitbucket Cloud and Data Center.

**Which programming languages are supported?**

Fully supported languages are Python, JavaScript, TypeScript, Go, Elixir, Java, C, C++, C

**How is Greptile priced?**

Starter is free for one active developer with 50 credits a month. Pro is $30 per seat per month with 50 credits per seat and $1 per extra credit. Enterprise pricing is custom.

**Can Greptile be self-hosted?**

Yes. Enterprise customers can self-host on-premises or in their own cloud via Docker Compose or Kubernetes with their own LLM providers, and air-gapped deployment is available.

**Is there a discount for open source or startups?**

Qualified non-commercial open source projects with an OSI-approved license use Greptile free, and pre-Series A startups under $2M revenue in the past 12 months get 50% off.

**Does Greptile have SOC 2 compliance?**

The site states SOC 2 compliance, with audit reports available on request, along with SSO and audit logs.