Attackers are using AI to find the holes in your code. We’ll help you find and fix them first, for free.
Through November 8, $1,000,000 in Deep Scan usage is on us.
Current users, former users, teams who've never touched us.
First come first served.
coderabbit.ai/blog/one-milli…
Through November 8, $1,000,000 in Deep Scan usage is on us.
Current users, former users, teams who've never touched us.
First come first served.
coderabbit.ai/blog/one-milli…
15
10
45
CodeRabbit is a SpaceX Super Intelligence Launch Partner! @SpaceXSI
Now in the Grok Build Plugin Marketplace: build with Grok Build and independently review changes with CodeRabbit.
Read the announcement coderabbit.ai/blog/coderabbi…
Now in the Grok Build Plugin Marketplace: build with Grok Build and independently review changes with CodeRabbit.
Read the announcement coderabbit.ai/blog/coderabbi…
3
10
20
A highlight from NVIDIA GTC Berlin: Jensen Huang spotlighting our work with @baseten on post-training specialized models for code review.
Proud to work with NVIDIA and Baseten to push the frontier of AI for software development!
Proud to work with NVIDIA and Baseten to push the frontier of AI for software development!
3
8
45
Congrats to TypesafeAI on the Series A!
At the first ever Jevathon, we watched developers build some seriously impressive apps on their new System One model.
Can't wait to see what's next!
At the first ever Jevathon, we watched developers build some seriously impressive apps on their new System One model.
Can't wait to see what's next!
we told @a16z we wanted to put intelligent software everywhere
they asked how much compute that would take
we said Uh Yes.
announcing our really big Series A
5
9
54
AI adoption needs more than a rollout.
Announcing DevClarity + CodeRabbit: hands-on AI enablement meets independent code review, helping software teams put AI to work and stay in control of what ships.
coderabbit.ai/partnerships/d…
Announcing DevClarity + CodeRabbit: hands-on AI enablement meets independent code review, helping software teams put AI to work and stay in control of what ships.
coderabbit.ai/partnerships/d…
1
2
16
AI coding tools keep getting better. What are we getting better at?
We sat with @kunalstwt to talk about the skills software engineers should invest in: understanding systems, solving useful problems, and taking responsibility for what ships.
Catch the full 1hr 16 video below!
We sat with @kunalstwt to talk about the skills software engineers should invest in: understanding systems, solving useful problems, and taking responsibility for what ships.
Catch the full 1hr 16 video below!
5
7
25
New home for your code, same rabbit on review.
CodeRabbit is a launch partner for Cursor Origin's app marketplace, bringing AI code review directly to Origin-hosted pull requests.
coderabbit.ai/blog/coderabbi…
CodeRabbit is a launch partner for Cursor Origin's app marketplace, bringing AI code review directly to Origin-hosted pull requests.
coderabbit.ai/blog/coderabbi…
Origin, Cursor’s code hosting platform, now supports over 20 integrations.
Connect your repos to tools for CI, deployments, code review, security, monitoring, and project management.
4
23
42
When an agent writes the code, who owns the result?
@trmlabs Rahul Raina and CodeRabbit’s Harjot Gill discuss the test evidence, human judgment, and team habits a company needs to ship at AI speed and trust the outcomes.
Watch the full video below!
coderabbit.ai/blog/the-featu…
@trmlabs Rahul Raina and CodeRabbit’s Harjot Gill discuss the test evidence, human judgment, and team habits a company needs to ship at AI speed and trust the outcomes.
Watch the full video below!
coderabbit.ai/blog/the-featu…
9
6
30
On September 30th alone, we completed 47,585 reviews.
The most-reviewed repo of the month was stablyai/orca with 5,629 reviews, followed by pingdotgg/t3code (@theo) and manaflow-ai/cmux.
Full top 10 in the article!
coderabbit.ai/blog/one-milli…
The most-reviewed repo of the month was stablyai/orca with 5,629 reviews, followed by pingdotgg/t3code (@theo) and manaflow-ai/cmux.
Full top 10 in the article!
coderabbit.ai/blog/one-milli…
1
0
1
1,049,817 open-source code reviews in September, a new monthly record!
That's 2.49x April's volume and up 14.4% from August.
"Not using it today would be like racing Formula One without a seatbelt or helmet." – @tannerlinsley, creator of TanStack
That's 2.49x April's volume and up 14.4% from August.
"Not using it today would be like racing Formula One without a seatbelt or helmet." – @tannerlinsley, creator of TanStack
13
24
72
We gave four security agents real vulnerabilities from the GitHub Advisory Database, with the advisory, CVE and patch withheld.
> CodeRabbit Security: 86.7%
> Devin: 73.3%
> Codex Security Plugin: 62%
> Claude Security: 40%
A finding only scored if it matched the real exploit path at the CWE, wrong path: zero.
Real our full write up below!
> CodeRabbit Security: 86.7%
> Devin: 73.3%
> Codex Security Plugin: 62%
> Claude Security: 40%
A finding only scored if it matched the real exploit path at the CWE, wrong path: zero.
Real our full write up below!
6
6
37
A coding agent can get an authorization check wrong, then write tests that confirm the mistake.
Everything passes.
That's why the review has to be independent of the system that wrote the change.
Here’s how CodeRabbit solves that:
coderabbit.ai/blog/why-agent…
Everything passes.
That's why the review has to be independent of the system that wrote the change.
Here’s how CodeRabbit solves that:
coderabbit.ai/blog/why-agent…
5
5
28
who went on the run this morning?
🐇 🏃♂️
🐇 🏃♂️
good morning, san francisco! ☀️
it’s day 1 of SF Tech Week, kicking off two weeks across SF and LA, with 2,600+ event submissions across both cities and 1,500+ events in SF alone.
Some events lined up for today, monday, october 5:
coffee, brunch & resets
• 8am - Rabbits on the - Coffee (BrewBird, Flex)
• 8:30am - TokenTechWalk (Vonage, Lovable)
• 8:30am - Women Brunch (Rho, Pivot North)
• 9am - Bfast (Deel, Ramp, AWS, SOMA)
• 10am - Padel (Deel, Human Interest, Sterling)
ai, agents & infra
• 8:30am - Open Weights (Bria, fal, LTX)
• 4pm - Video AI (Naver Ventures, Cooley)
• 4:30pm - Codex Meetup (OpenAI)
• 5pm - Production Agents (SurrealDB)
• 5pm - Agent Social (Manus, BuildClub)
• 5:30pm - Agents & APIs (Baseten, Postman, Rootly, Supabase, Prompting Co.)
hackathons, pitches & demos
• 3pm - Robotics & AI Pitches (AWS)
• 4pm - AI Build (Mem0, SVAI Hub, Gen Aca.)
• 4:30pm - Banking Hack Kickoff (Airwallex)
• 5pm - Hack Alcatraz (Cloudflare, Kling AI)
• 6pm - Demos After Dark (Fin, Clay)
founders & company building
• 9am - AI & Law (SimpleClosure, Carta)
• 10am - What’s Next (Techstars, Zendesk)
• 11am - Women’s Brunch (AWS)
• 2pm - AI Pitch (Auth0, Deel, Okta Ventures)
• 6pm - Early Hires (HigherPeople, Afore)
health & biotech
• 2pm - AI Health (SVB, Intelligence VC, Deel)
• 4pm - Preventive Health (Fenwick, a16z)
• 6:30pm - Women in Bio & Health (Fenwick)
vcs & fundraising
• 12pm - Lunch (Precursor, Stripe, BCV)
• 4pm - Down Under HH (Galileo, Relevance)
• 5pm - Shaun Maguire Fireside (Eon)
• 5:30pm - Chess Night (M13)
• 6pm - Dinner (JPMorgan, DealMaker)
• 6pm - Continual Learning (Fusion Fund)
art, games & nights out
• 5:30pm - Family Movie Night (Gigascale)
• 6pm - Giants Field Dinner (Airwallex)
• 6:30pm - Smash Bros & Agents (Dosu)
and more...
• 1pm - Why Pick the Boring (Valon)
• 2:30pm - Creativity & Play (GH, a16z)
• 4pm - Watts & Wisdom (a16z, Rillet)
• 6pm - Official Kickoff (Fireworks x a16z)
• 6:15pm - Cruise (MotherDuck)
follow @Techweek_ for updates and tag your photos #SFTechWeek
see you out there!
1
3
15
Name a better side quest
Today’s Build Personal Agents Hack crew:
@neondatabase @mastra @ExaAILabs @flydotio @usekernel @assistantui @agentmail
Plus Executor (@RhysSullivan) and @coderabbitai.
luma.com/build-agents
2
1
11
Your agent doesn't know Jev.
Most code calls LLMs the long way:
state → prompt → text → parse → if statement
Decision models like Jev skip the text and plug into your logic.
Here's 30 minutes with @typesafeai's @allietheicon on building with it.
Most code calls LLMs the long way:
state → prompt → text → parse → if statement
Decision models like Jev skip the text and plug into your logic.
Here's 30 minutes with @typesafeai's @allietheicon on building with it.
12
10
44
Your coding agent opened five more PRs while you were reviewing the first one.
CodeRabbit is joining the OpenAI Marketplace, which means your existing OpenAI spend commitment can now cover independent AI code review.
Let the agents keep shipping. We'll read the diffs.
8
CodeRabbit is joining the OpenAI Marketplace, which means your existing OpenAI spend commitment can now cover independent AI code review.
Let the agents keep shipping. We'll read the diffs.
8
4
9
28
Google Cloud wrote about how CodeRabbit is moving from AI code review into Agentic Change Management, and what we're building on Cloud Run, Cloud Storage and Gemini to get there.
Read the article here: cloud.google.com/blog/topics/st…
Read the article here: cloud.google.com/blog/topics/st…
7
2
9
Your agent worked all night. Do you merge what it wrote?
Francesco Bonacci (@francedot) of Cua (@trycua) wants his agents shipping while he sleeps, without waking up to a mess he has to clean up. The hard part is staying close enough to steer them.
On this episode of The Merge es the loop on agent tasks, what to do with low-quality AI-generated PRs, and why a proposed patch isn't a merge.
His take: more autonomy means review matters more, not less. You still need to be able to inspect the result and push back on it.
Francesco Bonacci (@francedot) of Cua (@trycua) wants his agents shipping while he sleeps, without waking up to a mess he has to clean up. The hard part is staying close enough to steer them.
On this episode of The Merge es the loop on agent tasks, what to do with low-quality AI-generated PRs, and why a proposed patch isn't a merge.
His take: more autonomy means review matters more, not less. You still need to be able to inspect the result and push back on it.
18
7
30