# HenryNdubuaku/maths-cs-ai-compendium

Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.

Repository: https://github.com/HenryNdubuaku/maths-cs-ai-compendium
Canonical: https://ross.abutalabs.com/products/maths-cs-ai-compendium
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: algorithms, deep-learning, jax, machine-learning, machine-learning-algorithms, math, mathematics, python, ai-textbook, artificial-intelligence, computer-science, computer-vision, linear-algebra, multimodal-learning, nlp, probability, reinforcement-learning, speech-processing, statistics
Last push: 2026-07-18T22:19:35+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 15
- inputs: {"age_days": 211, "days_push": 46, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7371, forks 901 (observed 2026-08-28T04:09:58.563781+00:00)

## What it is
An open-source online textbook covering mathematics, computer science, and AI/ML with an intuition-first approach, from linear algebra and probability to deep learning and NLP. It also ships an MCP server so AI assistants like Claude Code or Cursor can query the compendium as a knowledge base.

## Use cases
- learn the math behind machine learning from scratch
- prepare for AI/ML research or engineering interviews
- understand linear algebra and probability with intuition instead of dense notation
- study deep learning, NLP, and reinforcement learning fundamentals
- let an AI assistant answer questions from the textbook via MCP
- refresh statistics and calculus for ML work

## When to choose
- you want a free, intuition-driven alternative to dense academic textbooks
- you are self-studying the foundations of AI/ML
- you want an LLM-accessible knowledge base of math and ML concepts

## When to avoid
- you need a formal, rigorous reference with proofs
- you need a structured course with graded exercises and certification
- you need production ML tooling rather than learning material

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, mcp, developer-tools
- domain: tutorials, machine-learning, artificial-intelligence, mathematics, education
- platform: python
- tags: textbook, open-textbook, linear-algebra, probability, statistics, deep-learning, reinforcement-learning, nlp, computer-vision, intuition-first, mcp-server, interview-prep, web-server, typescript

## Member repositories
- HenryNdubuaku/maths-cs-ai-compendium (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:58.563781+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:38:23.688071+00:00, confidence not recorded.
  - readme: https://github.com/HenryNdubuaku/maths-cs-ai-compendium (fetched 2026-08-28T04:09:58.563781+00:00, sha 1575fd6f1298)
- Data as of 2026-08-30T08:39:29.467469+00:00.