Pinned Loading

1. ai-handoff-evaluator ai-handoff-evaluator Public

   A framework and AI tool that helps teams decide what AI should do, what humans should own & where the handoff should happen.

   JavaScript

2. confidence-aware-hybrid-rag confidence-aware-hybrid-rag Public

   Fully offline hybrid RAG concierge for luxury hotels with confidence aware query routing, FAISS HNSW semantic search, local Snoozy 13B LLM fallback, multi layer caching, and live metrics. No cloud.…

   Python

3. Equitable-Hiring-Audit Equitable-Hiring-Audit Public

   Multi-agent AI that audits hiring documents for bias. Three specialist agents analyse every document in parallel, a synthesis engine weighs their agreement, and a red team challenges every finding …

4. forge forge Public

   Deterministic pipeline for business documents. 8 workflows → structured data. Simulation Mode, provider agnostic AI. React+Vite+Python.

   JavaScript

5. llm-reliability-lab llm-reliability-lab Public

   An LLM reliability platform for evaluating, debugging and comparing AI pipelines across accuracy, hallucination, retrieval, cost & performance.

6. creditwise-ml creditwise-ml Public

   Credit risk ML pipeline with CatBoost, SHAP & LIME explainability, fairness monitoring and auto generated PDF reports built for auditability over accuracy.

   Python