[opensourcedex]

Kodus is a free, open source ai assisted coding project written in TypeScript and released under a custom open-source licence. It has 1,396 GitHub stars, 153 forks and 100 open issues, and was last pushed 4 hours ago. On this registry it ranks #20 of 24 tracked projects in AI Assisted Coding, with 5 head-to-head comparisons available. It gained 27 stars over the last 6 tracked days.

What is Kodus?

What it is

Kodus is an AI code review tool for teams that integrates with GitHub, GitLab, Bitbucket, and Azure Repos. It lives in the Developer Tools / AI Assisted Coding ecosystem and is distributed as a TypeScript monorepo. The project centers on Kody, an AI agent that reviews pull requests, flags risks by severity, and suggests fixes inside the normal review workflow.

The problem it addresses is the cost and inconsistency of manual code review. Teams often repeat the same feedback about architecture, security, testing practices, and repository conventions. Kodus reduces that overhead by letting teams define plain-language rules, connect their own model provider credentials, and run reviews in pull requests, the CLI, or CI/CD pipelines.

Key capabilities

  • It supports model-agnostic review through OpenAI, Anthropic, Google Gemini, Vertex AI, Novita, Llama, GLM, Kimi, or any OpenAI-compatible endpoint.
  • It lets teams bring their own provider keys, keeping model billing under their account with no hidden LLM markup.
  • Kody Rules let teams write review instructions in plain language and apply them across organizations, repositories, paths, or review scopes.
  • Kody reviews pull requests with context, assigns severity to risks, and suggests fixes directly in the pull request.
  • It tracks token consumption across AI code reviews so teams can understand cost drivers and keep model spend predictable.

Who uses it and how

  • Teams using GitHub, GitLab, Bitbucket, or Azure Repos can run Kody as a native pull request reviewer during existing merge request workflows.
  • Engineering leads can encode repeated review feedback once in Kody Rules, then apply it to selected repositories, paths, or review scopes.
  • Developers can run kodus review, kodus review --staged, or kodus review --prompt-only from a terminal to review a working tree, staged diff, branch, or commit.
  • Self-hosting teams can deploy the API, web dashboard, worker, and webhooks service on their own infrastructure, with self-hosted runners supported for source code privacy.

Getting started

Teams can start with Kodus Cloud, follow the self-host installation guide, or use the CLI for local and pipeline reviews. Contributors can clone the kodus-ai repository and run yarn setup to start the monorepo locally.

When to use it — and when not to

Kodus fits teams that want AI review tied to their own model provider accounts, custom review rules, and a self-hosted or pipeline-based workflow. It is less suitable for users who need a fully managed service with no infrastructure responsibility, because self-hosting requires operating the API, web application, worker, and webhook components. The facts show a very young project with a NOASSERTION license, zero contributors, and 100 open issues, so teams should verify governance and licensing before production adoption.

project readme (upstream, from github) — read inline

koduslogo

PRs Welcome Github Stars License

Website · Community · Docs · CLI Docs · Try Kodus Cloud · Self-Host Guide

🌐 English · Português (BR) · Español · 日本語 · 简体中文 · Français

Why Teams Choose Kodus

  • Model Agnostic: Use Claude, GPT-5, Gemini, Llama, GLM, Kimi or any OpenAI-compatible endpoint.
  • Zero Markup on LLM Costs: You pay model providers directly. No hidden multipliers.
  • Learns from Your Context: Kody adapts to your architecture, standards, and workflow.
  • You Set the Rules: Define custom review rules in plain language.
  • Privacy & Security: Source code is not used to train models, data is encrypted in transit and at rest, and self-hosted runners are supported. Self-hosted instances send one anonymous heartbeat per day (aggregated counters only — no code, names, or identifiers); opt out with KODUS_TELEMETRY_DISABLED=true. See Anonymous Telemetry.
  • Native Git Workflow: Works directly in PRs with GitHub, GitLab, Bitbucket, and Azure Repos.
  • CLI + CI/CD Ready: Run reviews locally and in pipelines.
  • Operational Impact: Track technical debt and delivery metrics while keeping review quality high.

Product Highlights

🔑 Bring Your Own Key
Connect your own provider credentials and choose the models behind Kodus reviews: OpenAI, Anthropic, Google Gemini, Vertex AI, Novita, or any OpenAI-compatible endpoint. Keep billing and usage under your own provider account, without hidden LLM markups.

Kodus BYOK model provider configuration


📈 Token Usage
Track token consumption across AI code reviews, understand cost drivers, and keep model spend predictable as adoption grows.

Kodus token usage dashboard


⚙️ Kody Rules
Kody Rules let teams define review instructions in plain language and apply them across organizations, repositories, paths, or specific review scopes. Kody uses those rules as context when reviewing pull requests, helping enforce architecture decisions, security expectations, testing practices, and repository-specific conventions without relying on reviewers to repeat the same feedback manually.

Kody rules


📊 Cockpit
Cockpit helps teams measure Kodus review effectiveness, Kody Rule health, repository health, and delivery metrics across the engineering workflow.

Kodus Cockpit showing AI code review pipeline health


🧩 Kody Issues
Automatically track unimplemented suggestions from closed pull requests, manage them by status, severity, category, and repository, and let Kody resolve them when the fix appears in a future PR.

Kodus Issues dashboard


🔎 See Kody reviewing a real pull request
Kody does more than summarize diffs. It reviews code with context, flags risks by severity, and suggests concrete fixes directly in the pull request.

Kody detecting a critical IDOR security issue in a pull request review />

In this example, Kody catches a critical IDOR risk where an organizationId query parameter could bypass tenant protection when passed as an array, then suggests an explicit runtime validation before the code is merged.

Get Started

Choose the workflow that matches how you want to use Kodus.

Try Kodus Cloud
Start reviewing pull requests without managing infrastructure.

Create a free account · View pricing 		Self-host Kodus
Deploy Kodus on your own infrastructure with control over data, models, and runtime configuration.

Installation guide
Use the CLI
Run AI code reviews from your terminal against a working tree, staged diff, branch, or commit.

kodus review
kodus review --staged
kodus review --prompt-only

CLI overview · Command reference · CI/CD 		Contribute Locally
Run the Kodus monorepo locally for development across the API, worker, webhooks service, web app, and local infrastructure.

git clone https://github.com/kodustech/kodus-ai.git
cd kodus-ai
yarn setup

Local quickstart

Monorepo Structure

Kodus is a monorepo with multiple applications and shared domain libraries.

kodus-ai/
├── apps/
│   ├── api/          # NestJS API
│   ├── web/          # Next.js dashboard
│   ├── worker/       # Review execution and queue consumers
│   └── webhooks/     # Git provider webhook ingestion
├── libs/             # Shared NestJS domain modules (incl. libs/llm — LLM/BYOK layer)
└── scripts/          # Dev, deploy, benchmark, and automation scripts
Path Purpose
apps/api Main NestJS API for authentication, organizations, teams, Kody Rules, integrations, permissions, and code review orchestration.
apps/web Next.js web application for the Kodus dashboard.
apps/worker Background service for code review execution, queue processing, suggestion checks, automation jobs, and monitoring tasks.
apps/webhooks Webhook ingestion service for GitHub, GitLab, Azure Repos, Bitbucket, and Forgejo events.
libs Shared NestJS domain modules used across Kodus applications.
libs/llm In-repo LLM/BYOK abstraction layer for model providers.

For full setup instructions, follow the Local Quickstart.

Open Source vs. Teams vs. Enterprise

| Feature | Kody Community
Community | Kody Teams

readme truncated — read the full docs on github

Frequently asked questions

Is Kodus free to use?

Kodus is open source. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Kodus do?

AI code review that learns your team's standards

What is Kodus written in?

Kodus is primarily written in TypeScript. Its source is publicly available at https://github.com/kodustech/kodus-ai, and it has 1,396 GitHub stars.