- About
- Open-source AI code review you can self-host with your own model. Open-source alternative to CodeRabbit.
- Catalogue
- No. 117
- Category
- AI
- GitHub stars
- ★ 0

Overview
Kodus is an open-source AI code reviewer that comments on pull requests in GitHub, GitLab, Bitbucket, Azure DevOps and Forgejo. You can run it on your own servers or use Kodus Cloud, with the AI model of your choice.
What it does well
Kodus works with Claude, GPT, Gemini, Llama or any OpenAI-compatible endpoint, and you pay the model provider directly with no markup. Its reviewer learns your architecture and standards, follows review rules you write in plain language, and runs from the command line or in CI pipelines. It also tracks token spend and delivery metrics.
Why it’s in the collection
Kodus gives teams AI code review without sending code to another vendor or paying a markup on model costs. The core is AGPL-licensed, with only enterprise features under a separate license.
On GitHub
- Stars
- 0
- Forks
- 0
- Commits
- 0
- Repository
- kodustech/kodus-ai
Languages
- TypeScript 94.2%
- JavaScript 3.6%
- Shell 1.9%
- Other 0.3%



