--- title: "LLMs-from-scratch vs AI-Compass" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/rasbt-llms-from-scratch-vs-tingaicompass-ai-compass" tools: ["rasbt-llms-from-scratch", "tingaicompass-ai-compass"] --- # LLMs-from-scratch vs AI-Compass *GraphCanon updated Jul 12, 2026* ## Verdict Pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; AI-Compass is Python; pick AI-Compass when aI-Compass 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. [AI-Compass](https://blog.csdn.net/sinat_39620217?spm=1011.2124.3001.5343) has 845 stars, 109 forks, and 1 open issues, last pushed Jul 10, 2026. Figures are from public GitHub metadata via [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch) and [AI-Compass's repository](https://github.com/tingaicompass/AI-Compass). | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [AI-Compass](/tools/tingaicompass-ai-compass.md) | | --- | --- | --- | | Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | “AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。 | | Stars | 98,899 | 845 | | Forks | 15,183 | 109 | | Open issues | 4 | 1 | | 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) | [AI-Compass](/tools/tingaicompass-ai-compass.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 38d | 1d | | Open issues (now) | 4 | 1 | | Full report | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | [trust report](/tools/tingaicompass-ai-compass/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; AI-Compass is Python. - Tags unique to LLMs-from-scratch: artificial-intelligence, attention mechanism, deep-learning, finetuning. - - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### Choose AI-Compass if… - AI-Compass is primarily Python; LLMs-from-scratch is Jupyter Notebook. - Tags unique to AI-Compass: agent, llm, llm-inference, llm-training. - 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 - a deeper learning experience. ## When NOT to use AI-Compass - 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 AI-Compass? LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. AI-Compass: “AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLMs-from-scratch over AI-Compass? Choose LLMs-from-scratch over AI-Compass when LLMs-from-scratch is primarily Jupyter Notebook; AI-Compass is Python; Tags unique to LLMs-from-scratch: artificial-intelligence, attention mechanism, deep-learning, finetuning; - You are an advanced practitioner aiming to fully understand the underpinnings of LLMs using PyTorch as your primary framework. ### When should I choose AI-Compass over LLMs-from-scratch? Choose AI-Compass over LLMs-from-scratch when AI-Compass is primarily Python; LLMs-from-scratch is Jupyter Notebook; Tags unique to AI-Compass: agent, llm, llm-inference, llm-training; 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 a deeper learning experience. ### When should I avoid AI-Compass? 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 AI-Compass more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 845). Stars measure visibility, not whether either tool fits your constraints. ### Are LLMs-from-scratch and AI-Compass open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to LLMs-from-scratch or AI-Compass? GraphCanon lists graph-backed alternatives at [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) and [AI-Compass alternatives](/tools/tingaicompass-ai-compass/alternatives) ([LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md), [AI-Compass markdown twin](/tools/tingaicompass-ai-compass/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-tingaicompass-ai-compass.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 AI-Compass? LLMs-from-scratch: Steady. AI-Compass: Very active. 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 AI-Compass? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust); [AI-Compass trust report](/tools/tingaicompass-ai-compass/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/_