Anthropic customers can now apply their existing Anthropic spend commitment toward CodeRabbit!
Simplified procurement. Consolidated AI spend.
A single Anthropic invoice for both.
CodeRabbit's review comments now cite their sources!
Bad guideline? delete it.
Irrelevant linked repo? disable it.
The review starts matching how your team actually works.
CodeRabbit's review comments now cite their sources!
Bad guideline? delete it.
Irrelevant linked repo? disable it.
The review starts matching how your team actually works.
Before an AI agent can actually get work done, it needs a whole new stack: an identity, and the ability to search, to read documents, to review code, and to pay.
Tomorrow in San Francisco, @GoKiteAI shares the stage at Agent Experience Demo Night, hosted by Sapient, with a
Your PR history shouldn't be a mystery.
Timeline View is live in CodeRabbit Review UI.
Filter by context, see what happened and why it happened.
Full explainability, so you can ship with confidence!
Introducing Overview 👁️
Everything a reviewer needs, before the first line of code.
> Draft status
> Merge conflicts
> Failing CI checks
> Requested changes from human reviewers
> Critical findings flagged by CodeRabbit
And so much more.
Sonnet 5 just dropped!
> Our benchmarks show the new model improves bug-catching precision on complex tasks, though overall recall dropped slightly.
> It behaves like a mid-level engineer, autonomously writing tests and self-correcting its own code during long-horizon tasks.
We ran Claude Sonnet 5 through our review benchmark.
> Cleaner comments
> Precision up by ~9%
> Deeper thinking
> Better coding skills
Read our full breakdown below!
Introducing Claude Sonnet 5, our most agentic Sonnet yet.
It makes plans, uses tools like browsers and terminals, and runs autonomously at a level that just a few months ago required larger and more expensive models.
CodeRabbit Agent now runs in Discord.
PR fixes, automations and code work, in the channels your community already uses.
Scoped so your server can't be misused.
Free for open source.
Two years ago everyone assumed AI would just make code review faster.
Same job, less time...right?
That assumption is the whole problem.
~1.7x more issues
Logic bugs up 75%
Security holes up around 2x.
The bottleneck has shifted right, from writing code to reviewing it.
