Open-Source AI Instruction Library

One Prompt. Top Models. Scored.

The only library that measures the same instruction file across major models with deterministic, reproducible scoring.

Explore Library GitHub Repo
What makes it different
Multi-Format Exports Direct transpilation for Cursor Rules, Windsurf, Claude Projects, and raw system prompts.
Compatibility Verified Benchmark any file across 8 models from Anthropic, OpenAI, Google, Qwen, Zhipu, and MiniMax with transparent scoring.
Structured UIR Consistent metadata schema powering validation, transpilation, and compatibility scoring.
Latest Models · OpenRouter Our Roster →
qwen/qwen3.7-flash New
Qwen: Qwen3.7 Flash
2026-07-27 $0.03 in $0.13 out
anthropic/claude-opus-5-fast New
Claude Opus 5 (Fast)
2026-07-24 $10.00 in $50.00 out
anthropic/claude-opus-5 New
Claude Opus 5
2026-07-24 $5.00 in $25.00 out
inclusionai/ling-3.0-flash:free New
Ling-3.0-flash (free)
2026-07-23 — in — out
poolside/laguna-s-2.1 New
Poolside: Laguna S 2.1
2026-07-21 $0.10 in $0.20 out
poolside/laguna-s-2.1:free New
Poolside: Laguna S 2.1 (free)
2026-07-21 — in — out
google/gemini-3.6-flash New
Google: Gemini 3.6 Flash
2026-07-21 $1.50 in $7.50 out
google/gemini-3.5-flash-lite New
Google: Gemini 3.5 Flash Lite
2026-07-21 $0.30 in $2.50 out
meituan/longcat-2.0 New
Meituan: LongCat 2.0
2026-07-20 $0.30 in $1.20 out