Bootstrap Kubernetes the hard way. No scripts.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

⚡️ Express inspired web framework written in Go

aws_s3 postgres extension to import/export data from/to s3 (compatible with aws_s3 extension on AWS RDS)

A simple adapter connection for any Streamlit app to use ChromaDB vector database.

🚀 The CLI for your next Chrome Extension

Data Engineering Zoomcamp is a free 9-week course on building production-ready data pipelines. The next cohort starts in January 2026. Join the course here 👇🏼

Examples in the MLX framework

Instant voice cloning by MIT and MyShell. Audio foundation model.

Curated list of project-based tutorials

Generative Models by Stability AI

MLX: An array framework for Apple silicon

This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

12 Weeks, 24 Lessons, AI for All!

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

Robust Speech Recognition via Large-Scale Weak Supervision

Demonstration application showing how Neo4j works with Google Vertex AI Generative AI

Web app that generates image from text/image/audio prompt

A microservice-based app using Flask, Express.js, Django, AMQP and Terraform

An AWS-serverless-based app that process 1GB transactions

Discover, try, install and share Streamlit re-usable bits we call "extras"!

Get protein embeddings from protein sequences

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

ezkl is an engine for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML). Use it from Python, Javascript, or the command line.