# kodustech/kodus-ai

AI Code Review with Full Control Over Model Choice and Costs.

Repository: https://github.com/kodustech/kodus-ai
Canonical: https://ross.abutalabs.com/products/kodus-ai
Homepage: https://kodus.io
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: ai, ai-agents, ai-code-review, ai-coding-tools, code-review, coding-assistant, generative-ai, hacktoberfest
Last push: 2026-08-26T18:04:56+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 37
- inputs: {"age_days": 523, "days_push": 7, "days_rel": 13, "gap_med": 0, "n_releases_24m": 272}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1326, forks 140 (observed 2026-08-28T04:04:22.792183+00:00)

## What it is
Kodus (Kody) is an open-source AI code review agent that reviews pull requests on GitHub, GitLab, Bitbucket, and Azure Repos. It is model-agnostic with bring-your-own-key support, customizable review rules, and can be self-hosted via Docker Compose or Helm or used as a cloud service.

## Use cases
- automate pull request code reviews with AI
- self-host an open-source CodeRabbit alternative
- enforce custom team coding standards in PR reviews
- use my own LLM API keys for code review without markup
- check PRs against Jira, Linear, or Notion requirements
- track technical debt from unaddressed review suggestions
- run AI code review locally or in CI/CD pipelines

## When to choose
- you want AI code review with full control over model choice and costs
- you need self-hosting for privacy or compliance reasons
- your team uses GitHub, GitLab, Bitbucket, or Azure Repos and wants native PR integration
- you want custom review rules in plain language and business-rule validation from project management tools

## When to avoid
- you want a fully free tool with no LLM token costs
- you need a lightweight static linter rather than LLM-based review
- you require a permissive license since the core is AGPLv3
- you prefer a vendor-managed solution with no infrastructure to run

## Facets
- artifact type: service
- maturity: active
- function: code-review, llm-inference, agent-framework, developer-tools, ci-cd
- domain: developer-tools, version-control, artificial-intelligence, large-language-models
- platform: self-hosted, cli, cloud
- tags: ai-code-review, code-reviewer, byok, model-agnostic, pull-request-review, coderabbit-alternative, agpl, technical-debt, git-integration, ai-agents, docker, web-server

## Member repositories
- kodustech/kodus-ai (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.792183+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:46:23.118592+00:00, confidence not recorded.
  - readme: https://github.com/kodustech/kodus-ai (fetched 2026-08-28T04:04:22.792183+00:00, sha d6e4e8a5867e)
  - homepage: https://kodus.io (fetched 2026-08-29T12:05:45.050100+00:00, sha e7574adb79c3)
  - site_page: https://docs.kodus.io/how_to_use/en/overview (fetched 2026-08-29T12:05:45.061496+00:00, sha a7650a7ab9de)
  - site_page: https://docs.kodus.io/changelog (fetched 2026-08-29T12:05:45.065415+00:00, sha e244b43c2b67)
  - site_page: https://kodus.io/pricing (fetched 2026-08-29T12:05:45.071789+00:00, sha eb6f4378498c)
- Data as of 2026-08-30T08:39:29.467469+00:00.