Marie Stephen Leo

cship. ⚡ A beautiful, fully customizable statusline for Claude Code - Starship-style TOML config, themeable colours, Nerd Font glyphs, and tunable cost/context/usage thresholds.

llm-structured-output-benchmarks. Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on tasks like multi-label classification, named entity recognition, synthetic data generation, etc.

bmad-autonomous-development. 🤖 Autonomous development orchestrator for the BMad Method. Runs fully autonomous, parallel, multi-agent pipelines through the full story lifecycle (create → dev → review → PR) driven by your sprint backlog and dependency graph.

OpenMicro. 🎮 Codex Micro functionality using any Gaming Controller on any Coding Harness!

stripnet. STriP Net: Semantic Similarity of Scientific Papers (S3P) Network

adventures-with-ann. All the code for a series of Medium articles on Approximate Nearest Neighbors

sagemaker-deployment. Jupyter Notebook

keras-model-selection. Choose the Best Keras Pre-Trained Model for Image Classification

heroku-apps. A monorepo with all my heroku apps

vibesense. 🕹️ Gamified Vibe Coding, with full controller support, mini-games, themes, and more!

nyc-taxi. New York Taxi dataset analysis using Python

twitter-ner. Collection of Named Entity Recognition NLP techniques focusing on Twitter data

stephenleo. Python

vibestats. ⚡ Auto-track Claude Code, Codex sessions across all your machines - GitHub heatmap + full analytics dashboard, zero setup

HVM-SPC. Case study of deriving Statistical Process Control limits

cloud-run-apis. Mono repo containing my cloud run APIs

gcp-examples. Repo with examples for using various GCP services with a heavy focus on Machine Learning

streamlit-apps. A mono-repo containing all my public Streamlit cloud apps