$ show HenryNdubuaku/maths-cs-ai-compendium
This repository is primarily an extensive educational compendium covering mathematics, computer science, and artificial intelligence from first principles to state-of-the-art topics. It contains over 100 markdown files organized into 20 chapters, each with detailed explanations, diagrams, and interactive coding tasks (primarily in Python/JAX). The repo also includes auxiliary tooling: a MkDocs-based documentation site with MathJax and a Pyodide in-browser Python runner that includes a JAX compatibility shim, and a TypeScript MCP (Model Context Protocol) server that provides programmatic access to the compendium content for AI assistants. While the vast majority of the repository is educational content rather than runnable software, the MCP server and interactive runner are functional application components. The compendium is well-structured and current, but the code examples are pedagogical (simplified, not production-ready) and the JAX shim is a fragile polyfill. The project is not a data research pipeline—it contains no datasets, experiment logs, or trained models.
The LLM identified 2 files worth highlighting for reuse:
A Model Context Protocol server that exposes tools for AI assistants to browse the compendium: list_topics, read_section, search, recommend, and get_examples. It reads markdown files and uses simple scoring for recommendations. This is a self-contained, reusable pattern for providing structured access to any markdown-based knowledge base via the MCP standard.
A JavaScript script that injects 'Run' buttons into Python code blocks on the documentation site, using Pyodide for in-browser execution. It includes a significant JAX compatibility shim that emulates jax.numpy, jax.grad, jax.jit, and other functions using NumPy, enabling educational code to run without the real JAX dependency. This pattern is reusable for any technical documentation that wants interactive Python demos with a polyfilled ML library.