train-llm-from-scratch vs awesome-llm-apps
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| train-llm-from-scratch | awesome-llm-apps | |
|---|---|---|
| Tagline | A method for training a Large Language Model (LLM) from scratch using Python. | 100+ AI Agent & RAG apps you can actually run — clone, customize, ship. |
| Stars | 8.1k | 117k |
| Forks | 1.1k | 17k |
| Open issues | 2 | 6 |
| Language | Python | Python |
| License | MIT | Apache-2.0 |
| Last pushed | Jun 24, 2026 | Jun 15, 2026 |
| Categories | LLM Frameworks, Model Training | AI Agents, LLM Frameworks |
train-llm-from-scratch
Repository offering scripts to train LLMs using PyTorch, detailing the process from raw text to aligned model with every part implemented manually from basic neural networks through transformer architecture, up to supervised fine-tuning methods.
Python
awesome-llm-apps
A repository containing a collection of AI agent and Retrieval-Augmented Generation (RAG) applications that are ready to be cloned, customized, and deployed. The projects cover various aspects such as AI agents, always-on agents, multi-agent teams, RAG techniques, voice agents, fine-tuning for specific use cases, and more.
Python