CodeRabbit says Codex helped it ship about 20 times more
First merged summary.
OpenAI says CodeRabbit uses Codex and GPT-6 Astra to review AI-generated code and ship far more software.
OpenAI published a customer story on November 9 about CodeRabbit, which uses OpenAI models and Codex to review and govern AI-generated code. CEO Harjot Gill says Codex let the same team ship about 20 times more software over six months, and he estimates he opened 2,500 to 3,000 pull requests in 30 days. He estimated GPT-6 Astra caught about half of known issues in CodeRabbit's internal review benchmark. CodeRabbit says it is used by more than 20,000 organizations and 150,000-plus open-source projects. CodeRabbit Secure uses Daybreak with Codex models to find and fix vulnerabilities, and a Codex-powered Slack bot can return a pull request for incident triage.
- CEO Harjot Gill says the same team shipped about 20 times more software in six months.
- Gill estimates GPT-6 Astra caught 50% of known issues in an internal benchmark.
- CodeRabbit says more than 20,000 organizations and 150,000-plus open-source projects use it.
- Gill estimated opening 2,500 to 3,000 pull requests in 30 days.
- GPT-6 Luna supports more subagents; GPT-6 Astra handles planning.
- CodeRabbit Secure uses Daybreak with Codex to find and fix vulnerabilities.
Timeline
dated events in the reporting · oldest first- Nov 9, 2026OpenAI published CodeRabbit customer story on Codex use. · OpenAI News
What each outlet adds
beyond the shared facts- OpenAI NewsCEO shipping estimate, benchmark catch rate, and user counts.
- Vendors
- OpenAI
- Organizations
- CodeRabbitMerge
- AI models
- GPT-6 AstraGPT-6 Luna
Coverage
oldest first · one row per article · UTCMerge integrates OpenAI GPT-6 Astra and Codex for product tools
Merge startup uses GPT-6 Astra, ChatGPT, and Codex to automate code reviews, marketing, workflows, and a dinner bot that cuts planning time from dozens of hours to 30 minutes per event.
CodeRabbit says Codex helped it ship 20 times more software
Its CEO estimates GPT-6 Astra caught about half the issues in CodeRabbit's internal review benchmark.