LLMs-from-scratch vs rtk

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

LLMs-from-scratchrtk
TaglineImplement a ChatGPT-like LLM in PyTorch from scratchCLI proxy reducing LLM token consumption by 60-90%
Stars99k69k
Forks15k4.3k
Open issues41.5k
LanguageJupyter NotebookRust
LicenseOtherApache-2.0
Last pushedJun 2, 2026Jul 7, 2026
CategoriesModel Training, LLM FrameworksInference & Serving, Developer Tools

LLMs-from-scratch

Repository containing code and instructions for developing, pretraining, and finetuning a GPT-like large language model (LLM) using PyTorch.

Jupyter Notebook

rtk

RTK is a high-performance CLI proxy written in Rust that significantly reduces the number of tokens consumed by Large Language Models (LLMs) when executing common development commands.

Rust