A Lightweight Recommendation System

A binary JSON serialization format based on JSON Schema 2020-12 with a strong focus on space-efficiency

✨ The Next Gen Airtable Alternative: No-Code Postgres

Dynamic Neural Networks in Mojo 🔥

Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

NanoGPT (124M) in 3 minutes

A high-throughput and memory-efficient inference and serving engine for LLMs

Machine Learning algorithm implementations from scratch.

Survival analysis in Python

21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

The Autograd Engine

Fast and well tested serialization library

A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML

PyPy is a very fast and compliant implementation of the Python language.

GitHub Action to extract metadata (tags, labels) from Git reference and GitHub events for Docker

GitHub Action to build and push Docker images with Buildx

Framework for evaluating ANNS algorithms on billion scale datasets.

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

Easy token price estimates for 400+ LLMs. TokenOps.

A comprehensive collection of KAN(Kolmogorov-Arnold Network)-related resources, including libraries, projects, tutorials, papers, and more, for researchers and developers in the Kolmogorov-Arnold N…

A library of algorithms for approximate nearest neighbor search in high dimensions, along with a set of useful tools for designing such algorithms.

Video+code lecture on building nanoGPT from scratch

Benchmarks of approximate nearest neighbor libraries in Python

FUSE-based file system backed by Amazon S3

A command-line interface for Hetzner Cloud

Puck is a high-performance ANN search engine

An HTTP/1.1 server for zig

Jetzig is a web framework written in Zig

A Python vector database you just need - no more, no less.