Kagento
LeetCode for AI Agents
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
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.
HN · launched Mar 27, 2026 · 11 upvotes (top 39%) · 0 views
Niche: ai benchmarking platforms · 145 launches, 4 in the last 7 days ▼ -56% · Explore this niche →
Category and tags
- Horizontal
- Observability & eval
- Developer
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 145 launches in ai benchmarking platforms →
Could you build this?
Partial The leaderboard and task UI are straightforward web development, but secure remote SSH agent access into isolated, multi-tenant execution sandboxes with automated evaluation requires specialized cloud infrastructure.
What it would actually take: The platform requires an orchestrator managing microVMs or hardened containers (such as Firecracker, gVisor, or Kubernetes with Kata Containers) provisioned per evaluation run. It demands custom SSH bastion/proxy servers to safely route automated agents into sandboxes, enforce strict network egress rules, measure resource utilization, and securely grade runtime outputs against benchmark test suites without vulnerability to arbitrary code execution escapes.
Discussion
1 comment analyzed.
Competitors
Other products that read as similar to this one : 2470 launches clear the similarity bar, closest 8 shown.
Attention rank: #1109 of 2471 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 149 days after the earliest competitor.
- ManyAgents · ph · 2026-10-26 · 92 upvotes · similarity 0.61
- Helm · github · 2026-09-20 · 10 upvotes · similarity 0.59
- Agent Maestro · ph · 2026-10-13 · 1 upvotes · similarity 0.58
- agent-board · github · 2026-10-16 · 22 upvotes · similarity 0.58
- Mission Control · hn · 2026-02-26 · 45 upvotes · similarity 0.56
- k_ai-agent-skills · github · 2026-09-14 · 14 upvotes · similarity 0.56
- AI Coding Agent Guardrails enforced at runtime · hn · 2026-04-20 · 5 upvotes · similarity 0.56
- kywai · ph · 2026-11-08 · 2 upvotes · similarity 0.55
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.