#1313th of 22 in Code review and testing
kodus-ai
AI pull request reviewer for GitHub, GitLab, Bitbucket, Azure DevOps and Forgejo
- Stars
- 1.6k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- TypeScript
1,009 on 3 Apr 20261,552 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Kodus reviews pull requests with an LLM you configure (bring your own key for OpenAI, Anthropic, Gemini, Vertex AI, Novita or any OpenAI-compatible endpoint). Reviews follow plain-language Kody Rules and can also run locally or in CI through a CLI. It is a TypeScript monorepo (NestJS API, worker, webhooks service, Next.js dashboard) that can be self-hosted or used as Kodus Cloud.
Who it is for: Teams wanting self-hostable AI pull request review with their own LLM
Strengths
- Supports five Git hosts: GitHub, GitLab, Bitbucket, Azure DevOps and Forgejo
- Bring-your-own-key model layer, including OpenAI-compatible and self-hosted models
- CLI reviews working tree, staged diff, branch or commit, and runs in CI/CD
- Custom review rules written in plain language, scoped by repo or path
Weaknesses
- Community edition limits Kody Rules to 10 and active plugins to 3
- Cockpit metrics are Teams and Enterprise only; SSO, RBAC and audit logs are Enterprise only
- Self-hosting needs a VM with 2 CPU cores, 8 GB RAM and 60 GB disk
- Self-hosted instances send a daily anonymous heartbeat unless disabled by environment variable
What it needs
- RAM ≥ 8 GB
- no GPU
- Docker + Compose
- Needs Docker, LLM provider API key or OpenAI-compatible endpoint
- Models: OpenAI, Anthropic, Google Gemini, Vertex AI, Novita
Quick answers
Is kodus-ai open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run kodus-ai with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Code review and testing
See all 22| Rank | Project | Score |
|---|---|---|
| 1 | playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit | 94 out of 100 |
| 2 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 91 out of 100 |
| 3 | react-doctorCLI that scans React codebases for state, performance, security and accessibility issues | 89 out of 100 |
| #4 | pr-agentLLM pull request reviewer that comments via /review, /describe and /improve | 86 out of 100 |
| #5 | e2eAI-driven end-to-end testing framework for web and mobile apps | 86 out of 100 |