catopt-category-theoretic-compositional (0.0.2)
Published 2026-04-20 12:18:01 +00:00 by forgeadmin
Installation
pip install --index-url About this package
Minimal MVP for CatOpt: category-theoretic compositional optimization (placeholder)
CatOpt: Category-Theoretic Compositional Optimization (MVP)
This repository hosts a minimal MVP of CatOpt to verify packaging, imports, and a tiny API surface used by the test suite. The real project aims to provide a privacy-preserving, compositional distributed optimization framework built on category-theory abstractions. This readme documents the current MVP scope and how to extend it.
- MVP surface: a simple add(a, b) function to validate packaging and imports.
- GoC: Graph-of-Contracts registry scaffold added to enable a minimal interoperability surface for adapters and contracts. See src/catopt_category_theoretic_compositional_/goc.py and the envelope_contract helper in the public API.
- Packaging: aligned with pyproject.toml, using setuptools to build a wheel.
- Extensibility: planned steps include a DSL for local problems, data contracts, an ADMM-like solver kernel, and adapters for edge devices.
Usage
- Run tests and build: ./test.sh
- Import in Python: from catopt_category_theoretic_compositional import add assert add(2, 3) == 5
Requirements
Requires Python: >=3.8