---
title: "graphrag vs LLMs-from-scratch"
type: "comparison"
canonical_url: "https://www.graphcanon.com/compare/microsoft-graphrag-vs-rasbt-llms-from-scratch"
tools: ["microsoft-graphrag", "rasbt-llms-from-scratch"]
---

# graphrag vs LLMs-from-scratch

Neutral, constraint-first comparison with live GitHub stats.

| | [graphrag](/tools/microsoft-graphrag.md) | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) |
| --- | --- | --- |
| Tagline | Graph-based Retrieval-Augmented Generation (RAG) system | Implement a ChatGPT-like LLM in PyTorch from scratch |
| Stars | 34,240 | 98,715 |
| Forks | 3,621 | 15,148 |
| Open issues | 158 | 4 |
| Language | Python | Jupyter Notebook |
| License | MIT | Other |
| Categories | Data & Retrieval, LLM Frameworks | Model Training, LLM Frameworks |

**Typed relationship:** graphrag _(related)_ LLMs-from-scratch

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon/graph?tool=microsoft-graphrag`](/api/graphcanon/graph?tool=microsoft-graphrag)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_