Deploy Kodus

Open-source AI code review for your pull requests, with your own LLM key

Deploy Kodus

Just deployed

/data/db

Just deployed

/var/lib/rabbitmq

/var/lib/postgresql/data

Just deployed

Deploy and Host Kodus on Railway

Kodus is an open-source AI code reviewer. Its agent, Kody, reviews every pull request on GitHub, GitLab, Bitbucket, Azure Repos or Forgejo, comments on bugs, security and style issues, and learns your team's rules. You bring your own LLM key (OpenAI, Anthropic, Gemini or any OpenAI-compatible model), so your code and costs stay under your control.

About Hosting Kodus

Kodus runs as several services: a Next.js web app, a REST API, a worker that runs the reviews, and a webhooks service your Git provider calls. It needs Postgres with pgvector, MongoDB and RabbitMQ with the delayed-message plugin. This template deploys all seven, pinned to Kodus self-hosted 2.2.11 and built from a public GitHub repo, so Railway notifies you when a new version lands. Every secret is generated, every database keeps its data on a volume, and the webhook URLs are wired to the webhooks service's own domain. After deploying, you sign up in the web app, add your LLM key and connect a repository.

Common Use Cases

  • Automatic AI review of every pull request, with your own LLM key and no per-seat SaaS pricing
  • Enforcing team coding rules ("Kody Rules") and catching bugs and security issues before merge
  • Keeping code review on infrastructure you control for private or regulated codebases

Dependencies for Kodus Hosting

  • Postgres with pgvector (Railway's Postgres), MongoDB 8 and RabbitMQ 4 with the delayed-message plugin, all included
  • An API key for an LLM provider (OpenAI, Anthropic, Google or OpenAI-compatible), added in the app after deploy

Deployment Dependencies

Implementation Details

After the deploy finishes:

  1. Open the web service's domain and sign up. The first account creates your organization and becomes its owner.
  2. Add your LLM key under Settings → BYOK. Reviews don't run without one.
  3. Connect a repository under Git Settings. Kodus registers the webhook on your provider, pointing at https://YOUR-WEBHOOKS-DOMAIN/github/webhook (or the gitlab, bitbucket, azure-repos or forgejo path).
  4. Open a pull request, or comment @kody start-review on one.

Sign-up stays open, as upstream ships it: anyone with the URL can create a separate organization of their own, but can't see yours. The api, MongoDB, RabbitMQ and Postgres services are private. Optional settings (SMTP or Resend e-mail, a server-wide LLM key API_OPEN_AI_API_KEY, OAuth login) go on the api, worker and webhooks services.

Updates: when the template repo bumps Kodus, Railway shows an "update available" notice on your project. Read the repo's CHANGELOG.md first; the api service runs the database migrations on start.

Why Deploy Kodus on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Kodus on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


Template Content

More templates in this category

View Template
Chat Chat
Chat Chat, your own unified chat and search to AI platform.

okisdev
117
View Template
Weaviate
Vector database with hybrid search and an API key-protected API

GitHub Locker
1
View Template
Möbius Personal AI OS
Self-hosted AI agent that builds and runs apps for you, with memory.

bento
1