Kodus AI

Active
GitHub TypeScript NOASSERTION

Description

Kodus AI is an open-source AI code review tool with full control over model choice and costs, automatically analyzing pull requests and delivering high-quality code review feedback.

Key Features

  • Model agnostic — supports Claude, GPT-5, Gemini, Llama, GLM, Kimi and any OpenAI-compatible endpoint
  • Zero markup on LLM costs — pay model providers directly with no hidden multipliers
  • Kody agent learns your code architecture, standards and workflows for personalized reviews
  • Custom review rules in plain language — define code review standards naturally
  • Privacy and security — source code not used for training, encrypted in transit and at rest, self-hosted runners supported
  • Native Git workflow integration supporting GitHub, GitLab, Bitbucket and Azure Repos

Use Cases

💡 Automate code reviews in PRs with high-quality feedback and technical debt tracking
💡 Unify team code standards through custom rules ensuring consistent review quality
💡 Integrate Kodus CLI in CI/CD pipelines for automated code quality checks
💡 Use Kody learning to adapt review feedback to team-specific architecture and preferences
💡 Deploy self-hosted version to protect enterprise code privacy while leveraging AI code review

Tags

coding typescript agent llm automation

Categories

💻 Coding Agent

Quick Start

Cloud: visit app.kodus.io to create a free account. Self-hosted: deploy with Railway template or follow manual installation docs. CLI: see docs.kodus.io/how_to_use/en/cli/overview for setup. Install Kodus App in GitHub/GitLab repo to start automatic PR reviews.
Visit GitHub

Related Projects