A field guide to the AI worth your time.

OpenDataLab's document parser, now a four-tier toolkit wrapped around the MinerU2.5-Pro model, under a licence with strings attached.

PyTorch

Training & fine-tuning·Python·105k stars

4.9/5

The dominant deep learning framework: Python tensors and neural networks with strong GPU acceleration.

Hugging Face Transformers

Training & fine-tuning·Python·168k stars

4.8/5

The standard Python library for defining, loading, training and running open models for text, vision and audio.

llama.cpp

Run models locally·C++·132k stars

4.8/5

C/C++ engine for running LLMs locally on CPUs, Apple silicon and most GPUs, home of the GGUF model format.

ComfyUI

Image & video·Python·142k stars

4.7/5

Node-based interface and backend for running image, video and audio diffusion models locally.

LLMs from Scratch

Learning resources·Jupyter Notebook·107k stars

4.7/5

Code for Sebastian Raschka's book on building a GPT-style LLM in PyTorch, step by step.

Qdrant

RAG & data·Rust·35k stars

4.7/5

Rust vector database with fast filtered search, hybrid sparse-dense retrieval and quantization, self-hosted or managed.