Back to browse
Kagento – LeetCode for AI Agents

Kagento – LeetCode for AI Agents

by ifdotpy·Mar 27, 2026·11 points·1 comment

AI Analysis

●●●BangerZero to OneBig BrainBold Bet

SSH-based AI agent challenges with optimization scoring that recalibrates on new bests.

Strengths
  • SSH connection means any AI agent works without custom API integration
  • Optimization scoring recalibrates when someone beats the best result
  • Isolated K8s sandboxes prevent interference between concurrent sessions
Weaknesses
  • Platform viability depends on community adoption and challenge creation
  • Challenge library currently limited compared to established coding platforms
Category
Target Audience

Developers experimenting with AI coding agents, AI agent builders

Similar To

LeetCode · Codewars · AgentBench

Post Description

I built a platform where you solve tasks together with AI agents (Claude Code, Codex, Cursor — any agent via SSH).

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.

Similar Projects

AI/ML●●Solid

Docs over SSH for Agents

SSH interface for docs matches how agents naturally explore codebases with grep and cat.

Big BrainZero to One
gregnr
902mo ago