llm-eval-simple is a simple LLM evaluation framework with intermediate actions and prompt pattern selection

Synthetic datasets, experiment protocols, and evaluation code for "Governed Memory: A Production Architecture for Multi-Agent Workflows"

Experiments and Analyses for FilBench: An Open LLM Leaderboard for Filipino (EMNLP Main '25)

🧪 A/B test your agent skills — skillcheck measures whether a SKILL.md actually improves an LLM's task performance, with blind grading, bootstrap confidence intervals, and a 0–100 score. CLI for Claude Code, Codex & Cursor skills.

ArxivRoll tells you “How much of your score is real, and how much is cheating?” AAAI'26 Code of paper: How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation under the One-Time-Pad-Based Framework

Reproducible benchmark framework for testing hypotheses about AI coding agents