Repolode
Submit
kodustech

kodustech/kodus-ai

Open source AI code review for pull requests that you can self-host, using the LLM provider of your choice.

Open-source alternative to:CodeRabbit

View on GitHubWebsite
Stars
1,514
Forks
178
Open issues
176
Last commit
2 hours ago

What is it?

Kodus is an open source AI code reviewer that comments on pull requests and merge requests. It works with GitHub, GitLab, Bitbucket, Azure DevOps, and Forgejo, and can run on your own servers or as a hosted service on Kodus Cloud.

The project follows a bring-your-own-key model: you connect credentials for providers such as OpenAI, Anthropic, Google Gemini, Vertex AI, or any OpenAI-compatible endpoint, so model usage is billed directly by your provider. Team-defined Kody Rules, written in plain language, guide what the reviewer checks across organizations, repositories, or paths. Kody Issues tracks unresolved suggestions from closed pull requests.

The monorepo contains a NestJS API, a Next.js dashboard, a worker for review jobs, a webhook service, and a CLI that can review a working tree, staged diff, branch, or commit, including in CI/CD pipelines.

Key features

  • 01Reviews pull requests on GitHub, GitLab, Bitbucket, Azure DevOps, and Forgejo.
  • 02Works with your own API keys for OpenAI, Anthropic, Gemini, and OpenAI-compatible endpoints.
  • 03Lets teams write review rules in plain language and scope them to repos or paths.
  • 04Tracks unimplemented suggestions from closed pull requests in Kody Issues.
  • 05Provides a CLI for reviewing local changes, staged diffs, branches, or commits.

Use cases

  • Teams that must keep source code inside their own infrastructure, including self-managed GitLab or Forgejo.
  • Organizations that want to choose and pay for their own LLM provider directly.
  • Enforcing repository-specific conventions and security checks on every pull request.
  • Running AI reviews from a terminal or CI pipeline before code is pushed.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/kodustech/kodus-ai.git
  2. 2

    Enter the project directory

    cd kodus-ai
  3. 3

    Run the local setup

    yarn setup

Things to know

  • Self-hosting requires Docker on a VM with at least 2 CPU cores, 8 GB RAM and 60 GB disk.
  • Licensed under AGPLv3, which is copyleft.
  • Self-hosted instances send one anonymous daily heartbeat unless telemetry is disabled.

Topics

#code-review#ai-code-review#pull-request#self-hosted#llm#byok#devtools#ai#ai-agents#ai-coding-tools

FAQ

What is kodus-ai?
Open source AI code review for pull requests that you can self-host, using the LLM provider of your choice. Kodus is an open source AI code reviewer that comments on pull requests and merge requests. It works with GitHub, GitLab, Bitbucket, Azure DevOps, and Forgejo, and can run on your own servers or as a hosted service on Kodus Cloud.
Is kodus-ai free to use? What license does it have?
kodus-ai is open source under the Other license. Check the license terms before using it in commercial products.
Is kodus-ai still maintained?
Actively maintained. The last commit to kodus-ai was on Oct 22, 2026.
What can I use kodus-ai for?
Teams that must keep source code inside their own infrastructure, including self-managed GitLab or Forgejo. Organizations that want to choose and pay for their own LLM provider directly. Enforcing repository-specific conventions and security checks on every pull request. Running AI reviews from a terminal or CI pipeline before code is pushed.
How do I install kodus-ai?
Clone the repository: git clone https://github.com/kodustech/kodus-ai.git Enter the project directory: cd kodus-ai Run the local setup: yarn setup
Where can I get kodus-ai?
The source code and installation instructions are on GitHub: https://github.com/kodustech/kodus-ai

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects