CodeRabbit
@coderabbitai.bsky.social
Supercharge your dev team with AI code reviews. Get your free trial now: https://coderabbit.ai!
Pinned
AI coding assistants are shipping more code...but also more bugs!
Our State of AI vs. Human Code Generation Report analyzed 470 real GitHub PRs.
The findings? AI‑coauthored PRs produced about 1.7× more issues than human‑only PRs!
Our State of AI vs. Human Code Generation Report analyzed 470 real GitHub PRs.
The findings? AI‑coauthored PRs produced about 1.7× more issues than human‑only PRs!
Letting users pick their favorite LLM feels empowering, but it destroys quality, consistency, and cost.
The best UX? No model dropdown at all.
Here’s why that choice should belong to evaluation, not preference.
👇
The best UX? No model dropdown at all.
Here’s why that choice should belong to evaluation, not preference.
👇
January 10, 2026 at 6:32 PM
Letting users pick their favorite LLM feels empowering, but it destroys quality, consistency, and cost.
The best UX? No model dropdown at all.
Here’s why that choice should belong to evaluation, not preference.
👇
The best UX? No model dropdown at all.
Here’s why that choice should belong to evaluation, not preference.
👇
Ranking every PR we've ever reviewed
January 9, 2026 at 4:35 PM
Ranking every PR we've ever reviewed
Prior to CodeRabbit, they'd tried multiple AI review tools and struggled to trust them.
But now they have:
> 70–85% of comments get accepted
> 0 follow‑up PRs
> A clear baseline for what “review ready” means.
Read more below 👇
www.coderabbit.ai/case-studie...
But now they have:
> 70–85% of comments get accepted
> 0 follow‑up PRs
> A clear baseline for what “review ready” means.
Read more below 👇
www.coderabbit.ai/case-studie...
Mastra finally found an AI code review tool their team can trust
CodeRabbit improved PR readiness, enabled broader team participation in code reviews, and reduced founder bottleneck, boosting merge confidence by 50%.
www.coderabbit.ai
January 7, 2026 at 4:59 PM
Prior to CodeRabbit, they'd tried multiple AI review tools and struggled to trust them.
But now they have:
> 70–85% of comments get accepted
> 0 follow‑up PRs
> A clear baseline for what “review ready” means.
Read more below 👇
www.coderabbit.ai/case-studie...
But now they have:
> 70–85% of comments get accepted
> 0 follow‑up PRs
> A clear baseline for what “review ready” means.
Read more below 👇
www.coderabbit.ai/case-studie...
Mastra ships a mission-critical TypeScript agent framework, and for their 1.0 release, they had:
> A fast-moving codebase
> 16 engineers
> Zero room for breaking changes.
Problem: Moving that fast without a reliable code review tool meant that bugs could slip through.
👇
> A fast-moving codebase
> 16 engineers
> Zero room for breaking changes.
Problem: Moving that fast without a reliable code review tool meant that bugs could slip through.
👇
January 7, 2026 at 4:59 PM
Mastra ships a mission-critical TypeScript agent framework, and for their 1.0 release, they had:
> A fast-moving codebase
> 16 engineers
> Zero room for breaking changes.
Problem: Moving that fast without a reliable code review tool meant that bugs could slip through.
👇
> A fast-moving codebase
> 16 engineers
> Zero room for breaking changes.
Problem: Moving that fast without a reliable code review tool meant that bugs could slip through.
👇
Our Bash-based Git worktree manager just hit 1K stars! ⭐
If you want 'git workflow' with better DX and AI tool integration, then go grab it!
If you want 'git workflow' with better DX and AI tool integration, then go grab it!
January 6, 2026 at 4:42 PM
Our Bash-based Git worktree manager just hit 1K stars! ⭐
If you want 'git workflow' with better DX and AI tool integration, then go grab it!
If you want 'git workflow' with better DX and AI tool integration, then go grab it!
Curious how open models like NVIDIA Nemotron can speed up your code reviews while cutting costs?
Read our latest article to see the architecture in depth 👇
www.coderabbit.ai/blog/codera...
Read our latest article to see the architecture in depth 👇
www.coderabbit.ai/blog/codera...
AI Code Reviews now support NVIDIA Nemotron
CodeRabbit now supports NVIDIA Nemotron, enhancing AI code reviews with faster, cost-efficient context gathering for its self-hosted customers
www.coderabbit.ai
January 5, 2026 at 10:25 PM
Curious how open models like NVIDIA Nemotron can speed up your code reviews while cutting costs?
Read our latest article to see the architecture in depth 👇
www.coderabbit.ai/blog/codera...
Read our latest article to see the architecture in depth 👇
www.coderabbit.ai/blog/codera...
CodeRabbit's AI code reviews now support NVIDIA Nemotron open models!
Self-hosted teams get faster, more cost-efficient reviews without sacrificing quality.
NVIDIA Nemotron 3 powers context gathering while frontier models handle deep reasoning!
Self-hosted teams get faster, more cost-efficient reviews without sacrificing quality.
NVIDIA Nemotron 3 powers context gathering while frontier models handle deep reasoning!
January 5, 2026 at 10:25 PM
CodeRabbit's AI code reviews now support NVIDIA Nemotron open models!
Self-hosted teams get faster, more cost-efficient reviews without sacrificing quality.
NVIDIA Nemotron 3 powers context gathering while frontier models handle deep reasoning!
Self-hosted teams get faster, more cost-efficient reviews without sacrificing quality.
NVIDIA Nemotron 3 powers context gathering while frontier models handle deep reasoning!
CodeRabbit CEO Harjot Gill will be joining the NVIDIA Live pregame as a panelist to discuss how open models help startups move faster and scale globally!
Tune in today at 11:45 a.m. PT before NVIDIA CEO Jensen Huang takes the stage!
Tune in today at 11:45 a.m. PT before NVIDIA CEO Jensen Huang takes the stage!
January 5, 2026 at 4:49 PM
CodeRabbit CEO Harjot Gill will be joining the NVIDIA Live pregame as a panelist to discuss how open models help startups move faster and scale globally!
Tune in today at 11:45 a.m. PT before NVIDIA CEO Jensen Huang takes the stage!
Tune in today at 11:45 a.m. PT before NVIDIA CEO Jensen Huang takes the stage!
We're excited to join "NVIDIA Live: Setting the Stage" with fellow leaders across AI infrastructure, open ecosystems, and physical AI!
We’ll dig into the ideas shaping the AI-native era and what it means for builders and businesses!
Tune in on January 5 at 11:45 a.m. PT 👇
We’ll dig into the ideas shaping the AI-native era and what it means for builders and businesses!
Tune in on January 5 at 11:45 a.m. PT 👇
January 4, 2026 at 8:12 PM
We're excited to join "NVIDIA Live: Setting the Stage" with fellow leaders across AI infrastructure, open ecosystems, and physical AI!
We’ll dig into the ideas shaping the AI-native era and what it means for builders and businesses!
Tune in on January 5 at 11:45 a.m. PT 👇
We’ll dig into the ideas shaping the AI-native era and what it means for builders and businesses!
Tune in on January 5 at 11:45 a.m. PT 👇
AI has enabled teams to ship faster in 2025! 🤖
But incidents, postmortems, and a 1.7x higher bug rate in AI‑written code showed the side effects of AI augmented speed.
In our new post, we detail how teams can make 2026 the year of AI quality!
www.coderabbit.ai/blog/2025-w...
But incidents, postmortems, and a 1.7x higher bug rate in AI‑written code showed the side effects of AI augmented speed.
In our new post, we detail how teams can make 2026 the year of AI quality!
www.coderabbit.ai/blog/2025-w...
December 31, 2025 at 3:57 PM
AI has enabled teams to ship faster in 2025! 🤖
But incidents, postmortems, and a 1.7x higher bug rate in AI‑written code showed the side effects of AI augmented speed.
In our new post, we detail how teams can make 2026 the year of AI quality!
www.coderabbit.ai/blog/2025-w...
But incidents, postmortems, and a 1.7x higher bug rate in AI‑written code showed the side effects of AI augmented speed.
In our new post, we detail how teams can make 2026 the year of AI quality!
www.coderabbit.ai/blog/2025-w...
North Pole postmortem just released.
Root cause: elves refactored the gift sorter “to make it more responsive,” introduced a textbook SQL injection, and one kid briefly qualified for 48,000+ presents.
Mitigation: mandatory CodeRabbit on every PR.
Full postmortem below.
Root cause: elves refactored the gift sorter “to make it more responsive,” introduced a textbook SQL injection, and one kid briefly qualified for 48,000+ presents.
Mitigation: mandatory CodeRabbit on every PR.
Full postmortem below.
December 22, 2025 at 8:15 PM
North Pole postmortem just released.
Root cause: elves refactored the gift sorter “to make it more responsive,” introduced a textbook SQL injection, and one kid briefly qualified for 48,000+ presents.
Mitigation: mandatory CodeRabbit on every PR.
Full postmortem below.
Root cause: elves refactored the gift sorter “to make it more responsive,” introduced a textbook SQL injection, and one kid briefly qualified for 48,000+ presents.
Mitigation: mandatory CodeRabbit on every PR.
Full postmortem below.
How to participate:
> Sign up to CodeRabbit
> Run CodeRabbit on a PR
> Share the Bug on Social media mentioning us
Let the best bug win (for now)!
Winners announced @ 0900PST this Friday!
coderabbit.ai
> Sign up to CodeRabbit
> Run CodeRabbit on a PR
> Share the Bug on Social media mentioning us
Let the best bug win (for now)!
Winners announced @ 0900PST this Friday!
coderabbit.ai
AI Code Reviews | CodeRabbit | Try for Free
AI-first pull request reviewer with context-aware feedback, line-by-line code suggestions, and real-time chat.
coderabbit.ai
December 22, 2025 at 4:44 PM
How to participate:
> Sign up to CodeRabbit
> Run CodeRabbit on a PR
> Share the Bug on Social media mentioning us
Let the best bug win (for now)!
Winners announced @ 0900PST this Friday!
coderabbit.ai
> Sign up to CodeRabbit
> Run CodeRabbit on a PR
> Share the Bug on Social media mentioning us
Let the best bug win (for now)!
Winners announced @ 0900PST this Friday!
coderabbit.ai
Announcing "Share the Bug" CodeRabbit Holiday giveaway! 🗣️
To celebrate the end of a great year, we are giving away:
> 1-year of individual CodeRabbit Pro
> 1-year subscription of Frontend Masters
> 1-year subscription to Egghead.io
To 10 people!
Entry rules in the thread! 👇
To celebrate the end of a great year, we are giving away:
> 1-year of individual CodeRabbit Pro
> 1-year subscription of Frontend Masters
> 1-year subscription to Egghead.io
To 10 people!
Entry rules in the thread! 👇
December 22, 2025 at 4:44 PM
Announcing "Share the Bug" CodeRabbit Holiday giveaway! 🗣️
To celebrate the end of a great year, we are giving away:
> 1-year of individual CodeRabbit Pro
> 1-year subscription of Frontend Masters
> 1-year subscription to Egghead.io
To 10 people!
Entry rules in the thread! 👇
To celebrate the end of a great year, we are giving away:
> 1-year of individual CodeRabbit Pro
> 1-year subscription of Frontend Masters
> 1-year subscription to Egghead.io
To 10 people!
Entry rules in the thread! 👇
Check out all the features of our new analytics dashboard in our latest blog post!
www.coderabbit.ai/blog/measur...
www.coderabbit.ai/blog/measur...
Measuring what matters in the age of AI-assisted development
Most AI tooling gives you vanity metrics. We go into the real numbers: what gets shipped and does it break production? Learn about our new dashboard.
www.coderabbit.ai
December 19, 2025 at 5:04 PM
Check out all the features of our new analytics dashboard in our latest blog post!
www.coderabbit.ai/blog/measur...
www.coderabbit.ai/blog/measur...
Most AI dev tools obsess over vanity metrics like lines of code and accepted completions.
The only metrics that matter:
> What actually ships
> Does it break production.
Our new analytics dashboard puts this visibility directly into the hands of engineering leaders!
The only metrics that matter:
> What actually ships
> Does it break production.
Our new analytics dashboard puts this visibility directly into the hands of engineering leaders!
December 19, 2025 at 5:04 PM
Most AI dev tools obsess over vanity metrics like lines of code and accepted completions.
The only metrics that matter:
> What actually ships
> Does it break production.
Our new analytics dashboard puts this visibility directly into the hands of engineering leaders!
The only metrics that matter:
> What actually ships
> Does it break production.
Our new analytics dashboard puts this visibility directly into the hands of engineering leaders!
The fix isn’t “less AI,” it’s smarter AI adoption:
– Properly review & QA
– Shift testing left and flag AI-authored PRs
– Expand chaos/resilience testing
– Train devs in AI literacy & secure coding
You can’t automate your way out of accountability.
www.coderabbit.ai/blog/why-20...
– Properly review & QA
– Shift testing left and flag AI-authored PRs
– Expand chaos/resilience testing
– Train devs in AI literacy & secure coding
You can’t automate your way out of accountability.
www.coderabbit.ai/blog/why-20...
2025 was the year the internet broke: Studies show increased incidents
Studies show more incidents in 2025 than in past years which lead to expensive downtime. What's causing it and what should we do as an industry?
www.coderabbit.ai
December 18, 2025 at 4:33 PM
The fix isn’t “less AI,” it’s smarter AI adoption:
– Properly review & QA
– Shift testing left and flag AI-authored PRs
– Expand chaos/resilience testing
– Train devs in AI literacy & secure coding
You can’t automate your way out of accountability.
www.coderabbit.ai/blog/why-20...
– Properly review & QA
– Shift testing left and flag AI-authored PRs
– Expand chaos/resilience testing
– Train devs in AI literacy & secure coding
You can’t automate your way out of accountability.
www.coderabbit.ai/blog/why-20...
2025 was the year the internet kept breaking 🔥 🌐
Outages are up, incidents are up, and AI-generated code is a big part of the story!
AI code now ships with around 1.7x more issues and more high‑risk vulnerabilities than human-written code.
Outages are up, incidents are up, and AI-generated code is a big part of the story!
AI code now ships with around 1.7x more issues and more high‑risk vulnerabilities than human-written code.
December 18, 2025 at 4:33 PM
2025 was the year the internet kept breaking 🔥 🌐
Outages are up, incidents are up, and AI-generated code is a big part of the story!
AI code now ships with around 1.7x more issues and more high‑risk vulnerabilities than human-written code.
Outages are up, incidents are up, and AI-generated code is a big part of the story!
AI code now ships with around 1.7x more issues and more high‑risk vulnerabilities than human-written code.
Reposted by CodeRabbit
Code review has quietly become a new bottleneck.
AI helps devs ship more code which means more PRs, more risk, and less time to review carefully.
So how about some AI Code Review to help with all the AI generated code? That's exactly what @coderabbitai.bsky.social built.
expo.dev/blog/ai-powe...
AI helps devs ship more code which means more PRs, more risk, and less time to review carefully.
So how about some AI Code Review to help with all the AI generated code? That's exactly what @coderabbitai.bsky.social built.
expo.dev/blog/ai-powe...
AI-powered code reviews for your Expo projects
CodeRabbit is an AI-powered code review platform that understands Expo. It catches real issues across your whole codebase before they hit production.
expo.dev
December 17, 2025 at 4:36 PM
Code review has quietly become a new bottleneck.
AI helps devs ship more code which means more PRs, more risk, and less time to review carefully.
So how about some AI Code Review to help with all the AI generated code? That's exactly what @coderabbitai.bsky.social built.
expo.dev/blog/ai-powe...
AI helps devs ship more code which means more PRs, more risk, and less time to review carefully.
So how about some AI Code Review to help with all the AI generated code? That's exactly what @coderabbitai.bsky.social built.
expo.dev/blog/ai-powe...
If your team is betting on AI in the stack, you need new guardrails:
> AI‑aware code review
> Stricter CI checks
> Better security + correctness automation.
Our full report breaks down the data, risk profile, and playbook for teams adopting AI!
www.coderabbit.ai/blog/state-...
> AI‑aware code review
> Stricter CI checks
> Better security + correctness automation.
Our full report breaks down the data, risk profile, and playbook for teams adopting AI!
www.coderabbit.ai/blog/state-...
AI vs human code gen report: AI code creates 1.7x more issues
We analyzed 470 open-source GitHub pull requests, using CodeRabbit’s structured issue taxonomy and found that AI generated code creates 1.7x more issues.
www.coderabbit.ai
December 17, 2025 at 4:50 PM
If your team is betting on AI in the stack, you need new guardrails:
> AI‑aware code review
> Stricter CI checks
> Better security + correctness automation.
Our full report breaks down the data, risk profile, and playbook for teams adopting AI!
www.coderabbit.ai/blog/state-...
> AI‑aware code review
> Stricter CI checks
> Better security + correctness automation.
Our full report breaks down the data, risk profile, and playbook for teams adopting AI!
www.coderabbit.ai/blog/state-...
On top of that, AI PRs are harder to live with!
Readability issues were 3.15× higher, formatting issues 2.66× higher, and unclear naming nearly 1.87× higher!
A quiet tax on reviews, onboarding, and long‑term maintainability.
Readability issues were 3.15× higher, formatting issues 2.66× higher, and unclear naming nearly 1.87× higher!
A quiet tax on reviews, onboarding, and long‑term maintainability.
December 17, 2025 at 4:50 PM
On top of that, AI PRs are harder to live with!
Readability issues were 3.15× higher, formatting issues 2.66× higher, and unclear naming nearly 1.87× higher!
A quiet tax on reviews, onboarding, and long‑term maintainability.
Readability issues were 3.15× higher, formatting issues 2.66× higher, and unclear naming nearly 1.87× higher!
A quiet tax on reviews, onboarding, and long‑term maintainability.