Kodus

Kodus is an open source AI code reviewer built around a core idea: your team's standards should drive reviews, not a vendor's defaults. It integrates at the pull request level across GitHub, GitLab, Bitbucket, and Azure DevOps, posting inline comments on diffs without storing your source code.

The main differentiator from tools like CodeRabbit is model agnosticism. You connect your own LLM (Claude, GPT-4, Gemini, Llama, or any OpenAI-compatible endpoint) and pay the provider directly. No markup on token costs.

Key capabilities:

• Custom rules – define review standards in plain language or pull from a built-in library. Reviews follow your guidelines consistently.
• Rule sync – Kody detects existing rule files from tools like Cursor, Copilot, and Windsurf automatically, so you don't rewrite what you already have.
• MCP integrations – connect Jira, Notion, or Linear so reviews account for specs and task context, not just the diff.
• Technical debt tracking – unimplemented suggestions become tracked issues, giving teams a running view of accumulated debt.
• Engineering dashboard – monitor deploy frequency, cycle time, bug ratio, and PR sizes in one place.
• Self-hosted runners – code never leaves your infrastructure if you need it that way.

Security is handled seriously. Source code isn't stored, isn't used for model training, and all data is encrypted in transit and at rest. SOC 2 compliance is supported.

Teams using Kodus report review times dropping from hours to minutes, with one team citing a 30% reduction in time spent on reviews. The platform subscription funds the product; token costs stay between you and your model provider.