--- title: "LLMs-from-scratch vs harness-books" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/rasbt-llms-from-scratch-vs-wquguru-harness-books" tools: ["rasbt-llms-from-scratch", "wquguru-harness-books"] --- # LLMs-from-scratch vs harness-books *GraphCanon updated Jul 11, 2026* ## Verdict Pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; harness-books is Python; pick harness-books when harness-books is primarily Python; LLMs-from-scratch is Jupyter Notebook. [LLMs-from-scratch](https://amzn.to/4fqvn0D) reports 99k GitHub stars, 15k forks, and 4 open issues, last pushed Jun 2, 2026. [harness-books](http://harness-books.agentway.dev/) has 2.6k stars, 308 forks, and 5 open issues, last pushed Apr 19, 2026. Figures are from public GitHub metadata via [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch) and [harness-books's repository](https://github.com/wquguru/harness-books). | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [harness-books](/tools/wquguru-harness-books.md) | | --- | --- | --- | | Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | 📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev | | Stars | 98,899 | 2,618 | | Forks | 15,183 | 308 | | Open issues | 4 | 5 | | Language | Jupyter Notebook | Python | | Adopt for | LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. | - | | Persona | - | - | | Runtime | - | - | | License | Other | - | | Categories | LLM Frameworks, Model Training | AI Agents, LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [harness-books](/tools/wquguru-harness-books.md) | | --- | --- | --- | | Days since push | 38d | 83d | | Open issues (now) | 4 | 5 | | Full report | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | [trust report](/tools/wquguru-harness-books/trust.md) | ## Decision facts: LLMs-from-scratch - **Adopt for:** LLMs-from-scratch is a project-oriented repository aimed at building PyTorch-based language models from the ground up, with detailed step-by-step instructions. ## Choose when ### Choose LLMs-from-scratch if… - LLMs-from-scratch is primarily Jupyter Notebook; harness-books is Python. - Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### Choose harness-books if… - harness-books is primarily Python; LLMs-from-scratch is Jupyter Notebook. - Tags unique to harness-books: agentic-ai, ai-agents, ai-engineering, claude-code. - Also covers AI Agents. ## When NOT to use LLMs-from-scratch - - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 - a deeper learning experience. ## When NOT to use harness-books - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## Common questions ### What is the difference between LLMs-from-scratch and harness-books? LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. harness-books: 📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLMs-from-scratch over harness-books? Choose LLMs-from-scratch over harness-books when LLMs-from-scratch is primarily Jupyter Notebook; harness-books is Python; Tags unique to LLMs-from-scratch: ai, artificial-intelligence, attention mechanism, deep-learning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I choose harness-books over LLMs-from-scratch? Choose harness-books over LLMs-from-scratch when harness-books is primarily Python; LLMs-from-scratch is Jupyter Notebook; Tags unique to harness-books: agentic-ai, ai-agents, ai-engineering, claude-code; Also covers AI Agents. ### When should I avoid LLMs-from-scratch? - If you are looking for a rapid deployment of an LLM without understanding its intricate structure - this tool requires extensive manual and conceptual work. - You prefer frameworks with automatic model generation or other high-level abstractions that simplify the process. This repository emphasizes manual creation, which is more time-consuming but offers丰 a deeper learning experience. ### When should I avoid harness-books? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### Is LLMs-from-scratch or harness-books more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 2,618). Stars measure visibility, not whether either tool fits your constraints. ### Are LLMs-from-scratch and harness-books open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to LLMs-from-scratch or harness-books? GraphCanon lists graph-backed alternatives at [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) and [harness-books alternatives](/tools/wquguru-harness-books/alternatives) ([LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md), [harness-books markdown twin](/tools/wquguru-harness-books/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/rasbt-llms-from-scratch-vs-wquguru-harness-books.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, LLMs-from-scratch or harness-books? LLMs-from-scratch: Steady. harness-books: Steady. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for LLMs-from-scratch and harness-books? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust); [harness-books trust report](/tools/wquguru-harness-books/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=rasbt-llms-from-scratch`](/api/graphcanon/graph?tool=rasbt-llms-from-scratch) - 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/_