LangFair — Peer-reviewed • Rank 14.9 • Science 95%

LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases - Published in JOSS (2025)

deepeval • Rank 28.2 • Science 54%

The LLM Evaluation Framework

propertyeval • Rank 0.7 • Science 57%

PropertyEval: Synthesizing Thorough Test Cases for LLM Code Generation Benchmarks using Property-Based Testing

nutcracker • Rank 1.9 • Science 54%

Large Model Evaluation Experiments

mlflow • Rank 35.5 • Science 10%

The open source developer platform to build AI/LLM applications and models with confidence. Enhance your AI applications with end-to-end tracking, observability, and evaluations, all in one integrated platform.

https://github.com/amazon-science/llm-code-preference • Rank 5.1 • Science 36%

Training and Benchmarking LLMs for Code Preference.

promptfoo • Science 26%

Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

https://github.com/ai4bharat/anudesh-frontend • Science 26%

https://github.com/ai4bharat/anudesh • Science 13%

An open source platform to annotate data for Large language models - at scale

https://github.com/cvs-health/uqlm • Science 36%

UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

tgcsm-circuit • Science 44%

The original containment framework for recursion-stable cognition, collapse-resistant logic, and LLM self-reflection.

milu • Science 41%

MILU (Multi-task Indic Language Understanding Benchmark) is a comprehensive evaluation dataset designed to assess the performance of LLMs across 11 Indic languages.

https://github.com/alan-turing-institute/prompto • Science 26%

An open source library for asynchronous querying of LLM endpoints

https://github.com/cedrickchee/vibe-jet • Science 26%

A browser-based 3D multiplayer flying game with arcade-style mechanics, created using the Gemini 2.5 Pro through a technique called "vibe coding"

https://github.com/amazon-science/idioms-incontext-mt • Science 23%

idioms in context dataset