Knitwise by Blore.AI shows how your team really works with Claude Code and Codex, then helps you agree one standard and keep it.
Free · Read-only · Your code never leaves your CI · Open-source assessment
Each developer has their own setup, rules and habits.
AI writes more code, faster, than teams can properly review.
You know AI is in every PR. You don't know how it's checked.
We ran Knitwise on one of our own repositories. The biggest finding wasn't in the code.
Knitwise — AI-Native Engineering Maturity Report
Observation
56 of 73 commits (77%) were pushed directly, without a pull request.
Top fixes
Real report from a Blore.AI repository, simplified.
Every score shows the evidence behind it.
Ranked by impact, so you know where to start.
Team-level only. Never individual developers.
A free, read-only check of how your team really ships AI-written code.
We set up one agreed standard in your repo, then align your team in a half-day session.
A weekly note when the standard starts to slip.
Every AI agent follows the same rules.
AI-written code gets tested before it's merged.
Reviews that actually catch problems.
A standard your team agreed on, not one imposed on them.
Your code never leaves your CI.
Open source: your security team can read every line. View on GitHub
Works with Claude Code, Codex, or both.
Free assessment plus a 30-minute walkthrough of your report, at no cost.
Get your free assessment Also an Authorized Microsoft AI Cloud Partner.knitwise-dev/assess) with read-only permissions; network calls only to api.github.com.CLAUDE.md and AGENTS.md, agent permissions, a test hook, a PR template and CI checks.