Now live

Writing code got easy.
Keeping a codebase healthy didn't.

AI coding assistants help your team ship faster. But code quality reviews haven't kept up. Patterns drift. Complexity grows. Octokraft tracks what all those AI-generated PRs are doing to your codebase as a whole.

Try Octokraft See how it works

The real problem

AI makes code generation fast.
It doesn't make your codebase better.

Every team we talk to has the same story. AI assistants generate PRs in minutes. Devs merge dozens a week. Each one looks fine. But nobody's tracking what all those changes are doing to the codebase as a whole.

Reviews get weird

You can't tell if someone actually understands what they committed or if they just accepted whatever the AI gave them. The more code you ship, the less anyone truly reviews.

Patterns drift quietly

Half the team writes error handling one way, the other half does something different. The "standard" is whatever the senior devs know. AI assistants don't know it at all.

The mess builds up

Each commit looks fine on its own. But over weeks the repo gets harder to change, and nobody can point to the moment it got bad. Quality just drifts.

What Octokraft does

The full picture.
Not just the PR.

Code Health

Know exactly where your codebase is degrading.

Security, tests, complexity, duplication, dead code, consistency, compliance, runtime. Weighted by what actually breaks production. Scored A+ through F.

Code Health Dashboard

Analysis

8

Languages supported. Zero config. We combine linters, AI review, and code graph analysis. Your stack is auto-detected.

Test Quality

Coverage tells you what runs. Not what it catches. We look at assertion quality, test-to-code ratio, and whether your mocks are replacing every real dependency.
PR Analysis

Pull Requests

See what a PR will do before you merge it

Intent classification, risk signals, health projection, convention drift, scope creep. Checked against your whole codebase, not just the changed files.

Architecture

Catch drift before it costs you a rewrite

Modularity, coupling, scalability, pattern adherence. Scored continuously. Docs that update themselves when the code changes.

Learn more

Conventions

Your patterns. Learned from your code.

Not a style guide someone wrote two years ago. Octokraft detects what your team actually does and tells you when new code doesn't match.

Convention Detection

How it works

Five minutes to first score.

1

Install the GitHub App

Pick your repos. Octokraft detects your stack, runs the analyzers, builds a code graph, and gives you a health score.

2

PRs get real context

A renamed function gets checked against every caller. A new endpoint gets compared to your existing patterns. Not just the changed lines.

3

Track health over time

You'll know when quality drops, when patterns drift, and when the architecture starts to shift. One dashboard for all your repos.

Integrations

Works with your AI setup.

Full MCP server for Claude Code, Cursor, Windsurf, and any MCP client. Push findings to GitHub Issues, Linear, or Jira. Bring your own AI keys. OpenAI, Anthropic, Azure, or self-hosted.

GitHub Claude Code Cursor Windsurf Linear Jira
View all integrations
❯ use octokraft mcp, connect to project octokraft, check PR review for #62 - fix issues
● octokraft - list_projects (MCP)
└ [
{
"created_at": "2026-03-11T21:01:21+01:00",
… +50 lines (ctrl+o to expand)
● octokraft - get_pr_analysis (MCP)
└ { "merge_readiness": "blocked", "findings": 4, ...
… +120 lines (ctrl+o to expand)
● octokraft - list_analysis_issues (MCP)
└ [CRITICAL] Database Migration Removal...
… +30 lines (ctrl+o to expand)
Source code never leaves your infrastructure
Never used for model training
Self-host with full data sovereignty

Built for real systems

Works across all your repos.

Most tools look at one repo at a time. Octokraft builds a graph across your whole system. Dependencies, symbols, cross-repo relationships. One dashboard that shows how your services actually connect.

Cross-repo health

Compare repos, track trends, find the one that's dragging everything down.

Impact propagation

A change in service A affects consumers in service B. See it before you merge.

Shared conventions

Same patterns enforced everywhere. What one team calls "how we do things" becomes the standard for all of them.

Pricing

Start free. Upgrade when your team needs weekly visibility.

Free

$0

For small teams, open source projects, and first trials.

  • Up to 5 contributors
  • Up to 10 repositories
  • 1 health assessment per month
  • Basic analysis, conventions, and ADR detection
Start free
Popular

Team

$24 /user/month

$19/user/month on annual billing

  • Unlimited contributors and repositories
  • Weekly health assessments and comparisons
  • Architecture reviews, drift alerts, and conventions
  • Jira, Linear, GitHub, Slack, and API access
Start with Team

Enterprise

$29 /user/month

Volume discounts, private deployment, and enterprise controls.

  • Everything in Team plus on-demand assessments
  • Multi-org support, audit logs, and advanced analytics
  • SSO, SAML, and private deployment
  • Dedicated support with volume discounts from 50 seats
Talk to sales

Ship faster.
Actually know what you're shipping.

The repo doesn't have to turn into a mess. Join the teams using Octokraft to keep their codebase healthy.

Try Octokraft Talk to us

Plans start at $50/mo. Get your first health score in minutes.