Projects
Open-source machine learning infrastructure and tooling, built from first principles. Each project page is written like documentation: problem, architecture, design decisions, benchmarks, and roadmap.
Meridian
Stable · v1.0A from-scratch grounded RAG engine over biomedical literature (PubMed). Custom BPE tokenizer, dense retriever, HNSW/IVF ANN, cross-encoder reranker, and NLI faithfulness verifier — no third-party pre-trained models. Every answer is cited, verified, or refused.
Polaris
Stable · v1.1A production-inspired NLP engineering platform for understanding text. The complete encoder-side stack — data, tokenization, collation, models, training, evaluation, deployment — from scratch on PyTorch tensors.
Zenith
Stable · v1.0A from-scratch generative NLP library — decoder-only language models and text generation. Llama-style internals (RoPE, RMSNorm, SwiGLU), KV-cached generation, speculative decoding, LoRA, instruction tuning. Matches the nanoGPT baseline.
Michi
Stable · v2.0道 — a local-first ML workbench. Independent CLI tools that profile datasets, evaluate models, and benchmark them with real statistical rigor. Automates the implementation, never the judgement.
More Projects
Smaller ML and applied-AI projects — experiments, prototypes, and deployments that shaped the flagship work. Each links to its GitHub repository.