Factory.ai coined the idea of "agent readiness" - measuring how prepared a codebase is for AI coding assistants - but kept their tool proprietary and cloud-only. Now an open-source alternative exists.
Kodus Agent Readiness is a free CLI that runs 39 checks across seven categories (linting, security, documentation, and more) to evaluate how smoothly AI agents like Claude Code, Cursor, and GitHub Copilot can work with your code. Everything runs locally. Your source code never leaves your machine.
The concept behind agent readiness is practical: AI coding assistants perform dramatically better on well-structured codebases. Consistent formatting, clear naming conventions, solid type coverage, and up-to-date documentation all reduce the number of hallucinations and wrong turns an AI agent takes. A codebase with no linter config, no tests, and vague variable names is going to get worse suggestions than one with strict conventions baked in.
Kodus packages that intuition into a scored report. You run the CLI, it scans your project, and you get a breakdown of where your codebase stands and what to fix first. Think of it as a code quality audit specifically tuned for the AI-assisted workflow.
The tool is self-hosted and available on GitHub under an open-source license. For teams already investing in AI coding tools but frustrated by inconsistent results, this kind of baseline measurement is useful. It won't magically make Copilot write better code, but knowing that your project scores poorly on, say, type coverage gives you a concrete thing to fix before blaming the AI.