Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

Notes from MSc Mathematical Engineering - Statistical Learning at Politecnico di Milano 📚

A Comprehensive Speech Processing Algorithms Library for research and production use

A comprehensive evaluation tool for verifying conversational AI applications.

Learning Deep Representations of Data Distributions

Machine Learning Engineering Open Book

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Run LLMs with MLX

Python modules for tokenizing Indian languages

Recent research papers about Foundation Models for Combinatorial Optimization

VIP cheatsheets for Stanford's CS 221 Artificial Intelligence

Unofficial Implementation of the paper "Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control", applied to gym environments

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Extremely fast Query Engine for DataFrames, written in Rust

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

A guideline for building practical production-level deep learning systems to be deployed in real world applications.

A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

NEAT (NeuroEvolution of Augmenting Topologies) is an evolutionary algorithm that evolves both the topology and weights of neural networks

.pdf Format Books for Machine and Deep Learning

A curated list of mathematical optimization courses, lectures, books, notes, libraries, frameworks and software.

MLOps example using Amazon SageMaker Pipeline and GitHub Actions

Free MLOps course from DataTalks.Club

Large Language Model (LLM) Systems Paper List

Tutorial on time series forecasting methods: from classical to llm-based approaches

Implementation of all RL algorithms in a simpler way

FinRL®: Financial Reinforcement Learning. 🔥

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.