Description
Kodus is an open-source AI code reviewer that analyses pull requests for bugs, security issues and performance problems. It checks each change against your team's own rules and business rules, and it can look for bugs across files and repositories, not just the lines that changed. You can talk to its reviewer, called Kody, inside the pull request, and it can track technical debt over time. Kodus is model agnostic: you can use Claude, GPT-4, Gemini, Llama or any OpenAI-compatible endpoint, and you bring your own model key with no markup. The company says you are charged only for the developers you include in the team, and that it does not train models on your code. The core is open source and can be self-hosted, so you can run the whole review on your own infrastructure, or use the cloud version. The site also publishes benchmarks of AI code review tools.…
Preview
Highlights
- AI review of pull requests
- Enforces your team's rules
- Bug detection across files and repos
- Talk to Kody inside the pull request
- Any model, your own keys
Ratings & Reviews
No ratings yet
Be the first to rate Kodus.
People also visit
Kodus FAQ
Is Kodus free?
The open-source core is free to self-host. The site also offers a cloud version, and it says you pay only for the developers you include.
Which AI models work?
The site says Kodus is model agnostic, so you can use Claude, GPT-4, Gemini, Llama or any OpenAI-compatible endpoint.
Does it train on my code?
No. The site says Kodus does not train its models on customer data.
Can I self-host it?
Yes. The site lists self-hosted AI code review that runs on your own infrastructure.
What are the best Kodus alternatives?
Popular alternatives to Kodus include Infinitcode AI, Openreview and diffay. See all Kodus alternatives




