#263 · Primary category: AI Coding Assistants
kodus-ai
AI Code Review with Full Control Over Model Choice and Costs.
Project last updated:08/28/26
GitHub Stars
1.3K
Forks
141
Contributors
31
License
Other
Why we included this project
Kodus is a self-hostable AI code review tool that plugs into the pull request flow on GitHub, GitLab, Bitbucket, or Azure Repos. The model is your call: bring your own API keys and point it at Claude, GPT, Gemini, Llama, or any OpenAI-compatible endpoint, and billing stays on your own provider account with no markup on tokens. The feature teams lean on most is Kody Rules, which lets you write review standards in plain language and have the agent apply them consistently across repos, so feedback quality stops depending on which reviewer happened to catch an issue. It also tracks token spend, follows up on suggestions from closed PRs that were never implemented, and reports delivery metrics, giving reviewers and leads a view beyond a single diff. Teams that want review assistance without surrendering control of cost or infrastructure get both from Kodus: model flexibility and self-hosting.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.