--- title: "LLMs-from-scratch vs aqueduct" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/rasbt-llms-from-scratch-vs-runllm-aqueduct" tools: ["rasbt-llms-from-scratch", "runllm-aqueduct"] --- # LLMs-from-scratch vs aqueduct *GraphCanon updated Jul 11, 2026* ## Verdict Pick LLMs-from-scratch when lLMs-from-scratch is primarily Jupyter Notebook; aqueduct is Go; pick aqueduct when aqueduct is primarily Go; 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. [aqueduct](https://aqueducthq.com) has 517 stars, 20 forks, and 11 open issues, last pushed Jun 7, 2023. Figures are from public GitHub metadata via [LLMs-from-scratch's repository](https://github.com/rasbt/LLMs-from-scratch) and [aqueduct's repository](https://github.com/RunLLM/aqueduct). | | [LLMs-from-scratch](/tools/rasbt-llms-from-scratch.md) | [aqueduct](/tools/runllm-aqueduct.md) | | --- | --- | --- | | Tagline | Implement a ChatGPT-like LLM in PyTorch from scratch, step by step | Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure. | | Stars | 98,899 | 517 | | Forks | 15,183 | 20 | | Open issues | 4 | 11 | | Language | Jupyter Notebook | Go | | 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 | Apache-2.0 | | 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) | [aqueduct](/tools/runllm-aqueduct.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Dormant (18%) | | Days since push | 38d | 1130d | | Open issues (now) | 4 | 11 | | Owner type | User | Organization | | Full report | [trust report](/tools/rasbt-llms-from-scratch/trust.md) | [trust report](/tools/runllm-aqueduct/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; aqueduct is Go. - License: LLMs-from-scratch is Other, aqueduct is Apache-2.0. - 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 aqueduct if… - aqueduct is primarily Go; LLMs-from-scratch is Jupyter Notebook. - License: aqueduct is Apache-2.0, LLMs-from-scratch is Other. - Tags unique to aqueduct: data, data-science, kubernetes, llm. - 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 aqueduct - Last GitHub push was 1130 days ago (dormant maintenance, Jun 7, 2023). Validate activity before betting a new project on aqueduct. - 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 aqueduct? LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step. aqueduct: Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.. See the comparison table for live GitHub stats and shared categories. ### When should I choose LLMs-from-scratch over aqueduct? Choose LLMs-from-scratch over aqueduct when LLMs-from-scratch is primarily Jupyter Notebook; aqueduct is Go; License: LLMs-from-scratch is Other, aqueduct is Apache-2.0; 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 aqueduct over LLMs-from-scratch? Choose aqueduct over LLMs-from-scratch when aqueduct is primarily Go; LLMs-from-scratch is Jupyter Notebook; License: aqueduct is Apache-2.0, LLMs-from-scratch is Other; Tags unique to aqueduct: data, data-science, kubernetes, llm; 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 aqueduct? Last GitHub push was 1130 days ago (dormant maintenance, Jun 7, 2023). Validate activity before betting a new project on aqueduct. 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 aqueduct more popular on GitHub? LLMs-from-scratch has more GitHub stars (98,899 vs 517). Stars measure visibility, not whether either tool fits your constraints. ### Are LLMs-from-scratch and aqueduct open source? Yes - both are open-source projects on GitHub (LLMs-from-scratch: Other, aqueduct: Apache-2.0). ### Where can I find alternatives to LLMs-from-scratch or aqueduct? GraphCanon lists graph-backed alternatives at [LLMs-from-scratch alternatives](/tools/rasbt-llms-from-scratch/alternatives) and [aqueduct alternatives](/tools/runllm-aqueduct/alternatives) ([LLMs-from-scratch markdown twin](/tools/rasbt-llms-from-scratch/alternatives.md), [aqueduct markdown twin](/tools/runllm-aqueduct/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-runllm-aqueduct.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 aqueduct? LLMs-from-scratch: Steady. aqueduct: Dormant. 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 aqueduct? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [LLMs-from-scratch trust report](/tools/rasbt-llms-from-scratch/trust); [aqueduct trust report](/tools/runllm-aqueduct/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/_