Learn it. Build it. Ship it for others.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

GRID: Generative Recommendation with Semantic IDs

A box of core libraries for recommendation model development

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

One webpage for every book ever published!

Build a modern LLM from scratch. Every line commented. Explained like we are five.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention

[KDD 2026] FCN: Fusing Exponential and Linear Cross Network for Click-Through Rate Prediction

A Python library for anomaly detection across tabular, time series, graph, text, and image data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

This repo contains state-of-the-art deep learning models for industrial anomaly detection, defect segmentation, detection, and classification, with other industrial machine vision applications.

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Build smaller, faster, and more secure desktop and mobile applications with a web frontend.

A JAX-native High Performance Eval Metrics Library

Effective and Scalable Recommendation Systems

Minimal, lightweight JAX implementations of popular models.

A curated model zoo for recommendation tasks

Sub-millisecond cache for ML/AI workloads. Parquets in, Arrow-Flight out.

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Awesome AI industry & research review

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023