Greptile
AI code review bot that indexes the whole repo and comments on pull requests with context.
why this verdict
Downgrade — pay for the workflow, not the AI
CodeRabbit and Qodo cover the headline feature free, so the $30/mo is now paying for the workflow around it.
- A named launch, not a vibe named, unlinked
- Claude Code review running natively inside GitHub Actions on every pull request. Anthropic, May 22, 2025 — no announcement link recorded yet.
- How much of the job it covers headline only editorial call
- The headline feature, but not the workflow, data or integrations around it.
- Is there a free way to do it? yes
- 2 of 3 listed replacements have a usable free tier: CodeRabbit and Qodo.
- What the call is worth $360/yr
- $30/mo at the entry paid tier — $360 a year per seat.
- Threatened by
- Anthropic
- Since
- May 22, 2025
- List price
- $30/mo
- Per year
- $360
The backstory
Greptile builds a graph of an entire codebase so its review comments understand cross-file consequences rather than just the diff. That was a clear edge while general models had small context windows. Anthropic now ships a Claude Code GitHub Action that reviews pull requests with repo access, and the model itself keeps improving at exactly this task. Greptile's memory of past reviews and its tuning against false positives are still worth paying for, which is why the diagnosis is wounded.
Escape hatches
switching could free up $360/yrAI pull request review with a free tier for public repos
coderabbit.ai open_in_newRuns reviews in CI through the official GitHub Action
claude.com open_in_newReview and test generation with an open-source PR agent
qodo.ai open_in_new2 of 3 replacements have a usable free tier.
