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 10 models from Anthropic, OpenAI, Google, Qwen, Zhipu, MiniMax, and Venice with transparent scoring.
Structured UIR Consistent metadata schema powering validation, transpilation, and compatibility scoring.
Latest Models · OpenRouter Our Roster →
anthropic/claude-opus-4.6-fast New
Anthropic: Claude Opus 4.6 (Fast)
2026-04-07 $30.00 in $150.00 out
z-ai/glm-5.1 New
Z.ai: GLM 5.1
2026-04-07 $0.95 in $3.15 out
google/gemma-4-26b-a4b-it New
Google: Gemma 4 26B A4B
2026-04-03 $0.12 in $0.40 out
google/gemma-4-26b-a4b-it:free New
Google: Gemma 4 26B A4B (free)
2026-04-03 — in — out
google/gemma-4-31b-it New
Google: Gemma 4 31B
2026-04-02 $0.14 in $0.40 out
google/gemma-4-31b-it:free New
Google: Gemma 4 31B (free)
2026-04-02 — in — out
qwen/qwen3.6-plus New
Qwen: Qwen3.6 Plus
2026-04-02 $0.33 in $1.95 out
z-ai/glm-5v-turbo New
Z.ai: GLM 5V Turbo
2026-04-01 $1.20 in $4.00 out
arcee-ai/trinity-large-thinking New
Arcee AI: Trinity Large Thinking
2026-04-01 $0.22 in $0.85 out