OSS Tanbou
View on GitHubProject website

Kodus — AI code review with team-controlled models and rules

OSS scale score 176.7OSS health 93Update pace 642 commits/30d
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
1,407
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 19, 2026

Overview

Kodus is an AI code review platform that reviews pull requests with repository context and team-defined rules. Teams can choose their LLM providers, bring their own keys, integrate with major Git platforms, use CLI/CI workflows, or self-host.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Apply team-specific review rules directly to pull requests

Kody Rules lets teams express architecture, security, testing, and repository conventions in plain language and use them as review context.

Sources: [2][3]

Control model choice, BYOK credentials, and model spend

Teams can choose providers and models, bring their own keys, and pay providers directly without an LLM markup layer.

Sources: [2][3]

For teams augmenting Git review while retaining policy control

It fits GitHub, GitLab, Bitbucket, and Azure Repos workflows where the same review policy should extend to CLI and CI/CD.

Sources: [2]

Keep human judgment in the loop and verify licensing and telemetry settings

AI review should augment rather than replace accountable human review. Self-hosted deployments should also review anonymous telemetry and Enterprise-license boundaries.

Sources: [2][4]

Official sources

  1. [1]kodustech/kodus-ai repository(2026-09-20)
  2. [2]Kodus README(2026-09-20)
  3. [3]Kodus documentation(2026-09-20)
  4. [4]Kodus dual license(2026-09-20)
Supplemental curator note

Kodus gives teams control over review rules, model/provider choice, credentials, and token spend. Most code is AGPL-3.0, while files or paths marked `.ee.` or `ee/` use a commercial Enterprise License.

Try it in 3 steps

  1. 1

    Get the source

    git clone --depth 1 https://github.com/kodustech/kodus-ai.git
  2. 2

    Enter the repository

    cd kodus-ai
  3. 3

    Check the official steps

    Continue with the commands in the README Installation, Quick Start, or Getting Started section.

    find . -maxdepth 1 -iname 'README*' -exec sed -n '1,220p' {} \; -quit
Check the official README

Growth

Growth trends · Last 30 days

1,407 Stars

Trend data is still being collected.

Development activity

Last 90 days · weekly

Commits (last 30 days)
642
Open PRs
19

Development activity is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • ai
  • ai-agents
  • ai-code-review
  • ai-coding-tools
  • code-review
  • coding-assistant
  • generative-ai
  • hacktoberfest
Stars
1,407
Forks
153
Watchers
8
Open issues
88
Contributors
26
Primary language
TypeScript
License
Not determined
Repository last updated
Sep 19, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.