Pinned Loading

1. mrm-prompt-bench mrm-prompt-bench Public

   A Python benchmark for comparing LLM prompting strategies on instruction-following document generation for Model Risk Management validation reports. It evaluates techniques like zero-shot, few-shot…

   Jupyter Notebook

2. evidence-graph evidence-graph Public

   A multi-agent AI research system that treats research as graph construction, explicitly surfacing contradictions to produce grounded, evidence-backed reports.

   Python

3. eval-fabric eval-fabric Public

   Pluggable evaluation orchestration framework for LLM and agentic systems. Defines versioned eval contracts, async runners, evaluator/judge plugins, reproducible traces, typed judgments, and OpenTel…

   Python 1

4. rag-comparison rag-comparison Public

   Educational comparison of KG-RAG, Hybrid RAG, and Agentic RAG patterns: same corpus, same questions, three pipelines.

   Jupyter Notebook