Self-hosted alternatives to Kodus
200 self-hosted apps like Kodus, closest match first.
Top picks
- O
Openreview
LaunchOpenReview is an open-source, self-hosted AI code review bot that runs on Vercel. You deploy it to your own Vercel account, connect a GitHub App, and then mention @openreview in a pull request comment to start a review, optionally with spec
Self-hosted
- M

Mira
LaunchMira is a self-hostable, open-source AI code reviewer. It connects to GitHub, GitLab, Forgejo or Bitbucket Cloud, watches pull and merge requests, and posts concise inline comments and walkthroughs. You choose the LLM, such as Anthropic, Op
Self-hosted
- A
AI Git Bot
LaunchAI-Git-Bot is the self-hosted AI workflow automation platform for Git repositories. Automate PR reviews, test generation, issue refinement, coding, documentation and translation sync — inside Gitea, GitHub, GitLab, and Bitbucket.
Self-hosted
- R

repowise
LaunchRepowise is a codebase intelligence tool that maps a repository's structure, git history, tests and decisions into one index, which the site says is kept current on every commit. The aim is to give coding agents such as Claude Code and Curs
Self-hosted
- P

Proval
LaunchSelf-hosted, privacy-first AI code review for GitLab, Forgejo, and GitHub. Bring your own model with Ollama, llama.cpp, or any OpenAI-compatible API.
Self-hosted
- R

Reviewbot
LaunchReviewbot is a self-hosted service for automated code review and static analysis, built by the Qiniu Cloud team for organisations with many repositories in several languages. Its docs explain the goal: one central service that applies linti
Self-hosted
More like Kodus
Review Board
Extensible and friendly code review tool for projects and companies of all sizes
About Kodus
Kodus
Open source AI code reviewer that analyzes pull requests
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.
- Price
- Open source
- Category
- AI
- Website
- kodus.io
