gabe-mousa/Apolien
AI Safety Evaluation Library
Implements chain-of-thought faithfulness evaluation by intervening in model reasoning steps to detect post-hoc explanations versus genuine reasoning, supporting local models via Ollama and cloud APIs (Claude, OpenAI) through a unified evaluator interface. Runs safety tests across configurable datasets with file-based logging of conversation transcripts and results. Currently focuses on faithfulness detection with extensible architecture for additional safety metrics like sycophancy and deception.
Available on PyPI.
Stars
5
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 09, 2025
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/gabe-mousa/Apolien"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/promptbench
A unified evaluation framework for large language models
uptrain-ai/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications....
levitation-opensource/Manipulative-Expression-Recognition
MER is a software that identifies and highlights manipulative communication in text from human...
microsoftarchive/promptbench
A unified evaluation framework for large language models
GSA/FedRAMP-OllaLab-Lean
The OllaLab-Lean project is designed to help both novice and experienced developers rapidly set...