npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@kodwai/cli

v1.8.0

Published

Kodwai CLI — AI-agent coding challenges and interview sessions

Readme

@kodwai/cli

The official CLI for kodwai — the AI-agent coding challenge platform for developers.

What is kodwai?

kodwai is a platform where developers solve real-world coding challenges using AI agents on their own machine. Use Claude Code, Cursor, or any AI coding agent you prefer — kodwai captures your session and scores how you collaborate with AI.

Getting Started

Sign in

kodwai login

This opens your browser, you approve the sign-in on kodwai, and the CLI stores a token in ~/.kodwai/config.json. It's the standard browser (OAuth loopback) flow: the CLI starts a temporary local server, the browser hands back a one-time code, and the CLI exchanges it for your token.

kodwai whoami     # show the signed-in account
kodwai logout     # sign out of this device

To switch accounts, run kodwai login again (or kodwai logout first) and choose "Use a different account" in the browser.

You don't have to log in first: challenge and submit will trigger the same browser sign-in automatically if you're not signed in.

Start a challenge

npx @kodwai/cli challenge <slug>

This will:

  1. Sign you in via the browser if needed (or use your stored token)
  2. Ask which AI agent you'll use (Claude Code, Cursor, etc.)
  3. Create a workspace with the problem statement and starter files
  4. Start the timer

Work with your AI agent in your own terminal, then submit:

kodwai submit

Your code, git history, test results, and AI agent traces are collected and scored.

How scoring works

  • 70% Objective — test pass rate, code quality, complexity, time efficiency, iteration patterns
  • 30% Analytical — AI-powered evaluation of problem solving, code quality, and agent collaboration (requires your Anthropic API key)

Run an interview session

If your interviewer sent you an invite email, use the session ID and token from the email:

npx @kodwai/cli start <session-id> --token <session-token>

This will:

  1. Fetch your problem statement and time limit from kodwai
  2. Set up a sandboxed workspace
  3. Start the timer
  4. Launch Claude Code (the interviewer pays for usage via a sandboxed key)

When time runs out or you type /exit in Claude Code, your session is auto-uploaded and AI-scored against the interviewer's rubric.

Commands

kodwai login                     Sign in via your browser
kodwai logout                    Sign out of this device
kodwai whoami                    Show the signed-in account
kodwai challenge <id-or-slug>    Start a developer coding challenge
kodwai submit                    Submit your challenge solution
kodwai start <session-id>        Join an interview session

Options:
  --local                        Use local dev (API localhost:8000, web localhost:3000)
  --api-url <url>                Override API URL
  --web-url <url>                Override web app URL (browser sign in)
  --token <token>                Session token (interview mode)

Local development

By default the CLI talks to production. To target a local stack, use --local (or set KODWAI_API_URL). The browser sign-in URL follows the API host, so a local API opens http://localhost:3000:

kodwai login --local
# equivalent:
kodwai login --api-url http://localhost:8000
# or, to apply to every command in the shell:
export KODWAI_API_URL=http://localhost:8000

Requirements

  • Node.js 20+
  • Git (auto-installed if missing)
  • An AI coding agent of your choice (Claude Code, Cursor, etc.)

Privacy

kodwai only collects data from your challenge workspace:

  • Code files from the challenge directory
  • Git history from the challenge session
  • AI agent traces scoped to the challenge time window
  • No data from other projects or sessions

The CLI source is publicly available. View the source.

Links

License

This project is licensed under the PolyForm Noncommercial License 1.0.0.

You may use, modify, and distribute it for personal, educational, research, and noncommercial purposes. Commercial use, including using this code to operate or promote your own product, is not permitted without a separate commercial license from kodwai.

See LICENSE for the full text. For commercial licensing inquiries, contact [email protected].

Contributing

See CONTRIBUTING.md. Security issues: see SECURITY.md.