One-click code review interview
No GitHub account or repo setup — candidates get a link and review code immediately.

SSH-based AI agent challenges with optimization scoring that recalibrates on new bests.
Developers experimenting with AI coding agents, AI agent builders
LeetCode · Codewars · AgentBench
Isolated sandbox environments, automated test scoring, global leaderboard. Tasks range from easy (AI one-shots it) to hard (requires human help).
Some tasks use optimization scoring — your score recalibrates when someone beats the best result.
Built it in 6 days as a solo founder. 100% of code written with Claude Code and Codex. Stack: Go, Next.js, K8s, Supabase, Stripe.
No GitHub account or repo setup — candidates get a link and review code immediately.
SSH interface for docs matches how agents naturally explore codebases with grep and cat.
Closes the loop: agents read eval traces to fix their own regressions.
Rust coding agent with ast-grep integration competing with Aider and Cursor.
Replaces SSH and tmux for managing Claude Code agents from your phone.
CarPlay coding sessions over SSH is a commute workflow nobody else is tackling.