LLMs-from-scratch vs rtk
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| LLMs-from-scratch | rtk | |
|---|---|---|
| Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch | CLI proxy reducing LLM token consumption by 60-90% |
| Stars | 99k | 69k |
| Forks | 15k | 4.3k |
| Open issues | 4 | 1.5k |
| Language | Jupyter Notebook | Rust |
| License | Other | Apache-2.0 |
| Last pushed | Jun 2, 2026 | Jul 7, 2026 |
| Categories | Model Training, LLM Frameworks | Inference & 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