Systems library
Filter by domain or stack to compare flagship case studies, supporting systems, and research projects that show implementation breadth.
Synthetic FHIR-style scoring service for 30-day readmission risk with schema validation, feature extraction, explainability, tests, model-card framing, and Dockerized FastAPI deployment.
Event-driven healthcare AI platform demonstrating HL7/FHIR interoperability, quality intelligence, SMART/CDS patterns, orchestration services, RabbitMQ, Redis, Postgres, and Dockerized infrastructure.
Local-first activation steering and representation-engineering lab with ActAdd-style vector extraction, FastAPI workbench APIs, React UI controls, model support notes, and reproducible artifacts.
Private/local PDF extraction pattern using PDF parsing, chunking, LangChain, Streamlit, Dockerized Ollama, analyst-authored criteria, and reviewable outputs.
Local-first agentic market intelligence workbench with public-signal ingestion, retrieval/storage services, planner agents, verification rules, structured reports, and Docker architecture.
Sports analytics forecasting and backtesting lab using 25+ years of historical NFL data, Elo baselines, XGBoost, logistic regression, ensembles, calibration, and probability-quality evaluation.
OCR plus LLM-enhanced parsing FastAPI service with image preprocessing, structured JSON outputs, confidence scoring, Docker variants, and API-first documentation.
Azure ML Prompt Flow retrieval-augmented generation demo using Jinja prompt templates, retrieval orchestration, and public wiki-style content.
Length-of-stay regression work using a Microsoft toy hospital dataset, Azure Notebooks, and baseline regression methods.
Healthcare quality RAG concept showing de-identification pseudocode, clinical-note preprocessing ideas, and HEDIS SSD retrieval workflow shape.
Early Streamlit dashboard scaffold that shows healthcare analytics UI foundations.
LangChain medication-recommendation concept retained as an experimental healthcare LLM example with explicit non-clinical boundaries.
t-SNE visualization concept for final-layer activations with slide images.
GPU comparison notes for healthcare AI workload planning across training, inference, medical imaging, agentic systems, and multi-model orchestration.
Machine-learning templates repository covering reusable preprocessing, evaluation, model selection, and visualization patterns.
Curation
The library favors systems with readable architecture, source-backed examples, and responsible public boundaries over raw repository volume.