WinNow
Last-30-days research ranked by authenticity, not raw engagement — scores every item on signal over hype.
Ranks recent research and writing by authenticity signals rather than engagement metrics, so genuinely useful work surfaces first.
Catalog entry only — a full write-up lands closer to release.
Related across catalogs
- PromptLeak ScannerSecurity project· Demo ready
Security test runner for AI applications — probes prompt injection, system prompt leakage, role-bypass, and unsafe-response patterns to find weaknesses before attackers do.
- RepoMemClaude Code plugin· Live
Persistent memory for AI coding agents — extracts observations from each Claude Code session, injects relevant context back at the next session start. Pure Python, SQLite+FTS5, zero deps.
- AgentArenaAI project· Demo ready
Benchmark AI coding agents head-to-head — paste a task, pick the agents, see who wins. Ranked leaderboard with per-agent scoring across speed/quality/efficiency.
- AI Review KitAI project· Demo ready
Portable AI code review workflows you can drop into any repository — production-focused review for bugs, regressions, security, performance, and missing tests.
- BonsaiAI project· Demo ready
Bonsai mode for AI agents — forces the smallest solution that works. YAGNI, enforced.
Want a heads-up when WinNow releases?