Hey Ph! 👋 @markmdev and I made Straude.
gave The NYTimes recently covered gave “Token Mixing” A trend sweeping through Silicon Valley – the idea that AI token consumption is becoming the new status metric for AI-native builders. Companies like Meta, OpenAI, and Shopify are tracking this on internal dashboards. Jensen Huang proposed giving engineers a token budget of up to 50% of their salary.
At the same time, I found the agent coding experience to be quite isolating. You rotate through dozens of agents and spend thousands of tokens, but you have no way to track, compare, or share the journey. And since there’s no “town hall” where AI builders gather, you can’t easily learn how the best builders are pushing these tools to their limits.
Straude corrects that:
A command `npx straude` logs your cloudcode or codecs sessions: tokens used, spent, models used. Support for other agents is coming soon.
Compete on global leaderboards, build your stream, and be inspired by what the top 1% of AI creators are pushing every day.
Privacy-first: Only aggregate statistics leave your machine, no code or session history.
Zero install, zero configuration.
How it works:
Sign up at straude.com
Run `npx straude` at the end of cloudcode/codex session.
Your stats are automatically synced to the feed and leaderboard.
It is completely free. The project is open source on GitHub.
Strava made solitary sport (walking) social and fun. Straude does the same for agentive engineering. You wouldn’t train for a marathon without logging your miles. Why would you burn through tokens without tracking on Straude?
We’d love for you to sign up, log your first session, and share Straude with the friend you know who burns the most tokens 🔥
We’d love your feedback — what features would you like to see next?
